One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning | Paper Citation Record

Observation 89918a94-494d-41d8-a327-a7c36f488a00 · outbound

This paper cites Code Llama: Open Foundation Models for Code.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Code Llama: Open Foundation Models for Code

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:51:07.492271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2b96264c-ffd6-4f02-a35e-3acf55c8c0d9 · outbound

This paper cites Llemma: An open language model for mathematics.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Llemma: An open language model for mathematics

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.108996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7c969739-741f-4208-b269-6ec855d327a3 · outbound

This paper cites ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:51:07.497023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 92470023-da72-491e-afa9-b976441be1cd · outbound

This paper cites LoRA: Low-rank adaptation of large language models.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning LoRA: Low-rank adaptation of large language models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.101675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f226b1aa-5ade-40b4-8542-9c4be168fbc0 · outbound

This paper cites QLoRA: Efficient finetuning of quantized LLMs.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning QLoRA: Efficient finetuning of quantized LLMs

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.033598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8d569b51-4092-4c13-b556-ed97e9458c76 · outbound

This paper cites PiCa: Parameter-Efficient Fine-Tuning with Column Space Projection.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning PiCa: Parameter-Efficient Fine-Tuning with Column Space Projection

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:51:07.449527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7416cd68-0f36-495a-aa68-495c57c6331c · outbound

This paper cites QWHA: Quantization-aware walsh-hadamard adapta- tion for parameter-efficient fine-tuning on large language models.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning QWHA: Quantization-aware walsh-hadamard adapta- tion for parameter-efficient fine-tuning on large language models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:17.989262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7881de0b-e4ec-4655-b723-8b3f7deed8d8 · outbound

This paper cites Parameter-efficient fine-tuning methods for pretrained language models: A critical review and assessment.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Parameter-efficient fine-tuning methods for pretrained language models: A critical review and assessment

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.116948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 139c5c5f-676f-4dd1-b9b1-d52b2771f7a8 · outbound

This paper cites Parameter-efficient tuning with special token adaptation.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Parameter-efficient tuning with special token adaptation

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.021254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 48f4c21c-0240-438d-9e14-6a8c139b33a9 · outbound

This paper cites Multitask prompt tuning enables parameter-efficient transfer learning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Multitask prompt tuning enables parameter-efficient transfer learning

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:17.998234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7bf84b4f-27b8-45b9-9ade-b2f373b34873 · outbound

This paper cites Galore: Memory-efficient LLM training by gradient low-rank projection.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Galore: Memory-efficient LLM training by gradient low-rank projection

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.487625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0132444b-33e5-4745-b30f-269805efd0ee · outbound

This paper cites DoRA: Weight-decomposed low-rank adaptation.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning DoRA: Weight-decomposed low-rank adaptation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.490983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0bf552d5-29a1-4260-8ed5-cb0402630aa4 · outbound

This paper cites Make pre-trained model reversible: From parameter to memory efficient fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Make pre-trained model reversible: From parameter to memory efficient fine-tuning

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.497128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cffdcafe-5ec0-45ab-9845-35582f2bc84d · outbound

This paper cites SVFT: Parameter-efficient fine-tuning with singular vectors.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning SVFT: Parameter-efficient fine-tuning with singular vectors

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.499964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c7bdf4d7-7a5d-49fd-8d87-0bce76dc4ecc · outbound

This paper cites Increasing model capacity for free: A simple strategy for parameter efficient fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Increasing model capacity for free: A simple strategy for parameter efficient fine-tuning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.477820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 28a3dee9-4dae-4602-8100-5e898db53f11 · outbound

This paper cites LESS: Selecting influential data for targeted instruction tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning LESS: Selecting influential data for targeted instruction tuning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.506004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cc493171-0578-4a97-ad6a-4512eb5c07b8 · outbound

This paper cites Upweighting easy samples in fine-tuning mitigates forgetting.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Upweighting easy samples in fine-tuning mitigates forgetting

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.121092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ba7c2cf1-fc06-4cba-aa50-6364c9c921e6 · outbound

This paper cites Skrull: Towards efficient long context fine-tuning through dynamic data scheduling.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Skrull: Towards efficient long context fine-tuning through dynamic data scheduling

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.420306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 01d5fe9f-f963-41ce-b08c-d746f4de0b68 · outbound

This paper cites Difficulty is not enough: Curriculum learning for llms fine-tuning must consider utility.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Difficulty is not enough: Curriculum learning for llms fine-tuning must consider utility

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.345146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dec6fa5d-57c1-4734-89b1-6f7e81ad87a3 · outbound

This paper cites Deft-ucs: Data efficient fine-tuning for pre-trained language models via unsuper- vised core-set selection for text-editing.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Deft-ucs: Data efficient fine-tuning for pre-trained language models via unsuper- vised core-set selection for text-editing

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.342209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1c1947d3-5aa3-4215-92fe-9c3e05d5685e · outbound

This paper cites DELIFT: Data efficient language model in- struction fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning DELIFT: Data efficient language model in- struction fine-tuning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.347994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ed268af7-c418-4feb-8518-fb27ad75c007 · outbound

This paper cites Task-specific skill localization in fine-tuned language models.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Task-specific skill localization in fine-tuned language models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.353632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d4055f8d-0240-4570-9954-c04dbe493611 · outbound

This paper cites Sparse is enough in fine-tuning pre-trained large language models.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Sparse is enough in fine-tuning pre-trained large language models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.331645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7d99548f-0716-49f2-b87c-529bb10fbecc · outbound

This paper cites S$^{2}$FT: Efficient, scalable and generalizable LLM fine-tuning by structured sparsity.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning S$^{2}$FT: Efficient, scalable and generalizable LLM fine-tuning by structured sparsity

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.325163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3381605a-0984-4300-a049-1e6274ced326 · outbound

This paper cites LISA: Layerwise importance sampling for memory-efficient large language model fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning LISA: Layerwise importance sampling for memory-efficient large language model fine-tuning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.509231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1d164f14-a5ad-460e-a573-66cefa1005fe · outbound

This paper cites SMT: Fine-tuning large language models with sparse matrices.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning SMT: Fine-tuning large language models with sparse matrices

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.073276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 731bfbd5-acc9-4f77-8d1e-09437f454a46 · outbound

This paper cites LIFT the veil for the truth: Principal weights emerge after rank reduction for reasoning-focused supervised fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning LIFT the veil for the truth: Principal weights emerge after rank reduction for reasoning-focused supervised fine-tuning

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.318651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e70eb35c-227f-415c-bc71-94ee5d3c8f74 · outbound

This paper cites Pay attention to small weights.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Pay attention to small weights

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:17.993506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fa7c2943-6b3d-4e29-926b-10ccd408a94f · outbound

This paper cites Jerry Liu.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Jerry Liu

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T18:51:07.462583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8d539e49-d752-4538-9d02-5fed955331a4 · outbound

This paper cites Gast: Gradient-aligned sparse tuning of large language models with data-layer selection.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Gast: Gradient-aligned sparse tuning of large language models with data-layer selection

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.085372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1a7a411b-c0b4-4028-b713-2479d85c0f7c · outbound

This paper cites FisherSFT: Data-efficient supervised fine-tuning of language models using information gain.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning FisherSFT: Data-efficient supervised fine-tuning of language models using information gain

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.315250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 96a7464a-cedf-4a98-bf25-6f2574f51c89 · outbound

This paper cites Boosting multi-domain fine-tuning of large language models through evolving interactions between samples.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Boosting multi-domain fine-tuning of large language models through evolving interactions between samples

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.321664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ff725076-b30a-4925-aba5-916a354748a8 · outbound

This paper cites Joint selection for large-scale pre-training data via policy gradient-based mask learning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Joint selection for large-scale pre-training data via policy gradient-based mask learning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.328445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 936ee5ac-eeb7-4045-aef5-3041bc7d0bbb · outbound

This paper cites GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:02:09.973489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 018ab265-2dca-49b9-bf32-2e8ba52fbf5b · outbound

This paper cites SPICE: Submodular penalized information–conflict selection for efficient large language model training.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning SPICE: Submodular penalized information–conflict selection for efficient large language model training

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.339169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e9dbd2cd-abdd-4ea5-b390-42f644717438 · outbound

This paper cites Tuning layernorm in attention: Towards efficient multi-modal LLM finetuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Tuning layernorm in attention: Towards efficient multi-modal LLM finetuning

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.312363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f36ec71c-1d54-4629-9640-41e36af9cc1b · outbound

This paper cites SparseloRA: Accelerating LLM fine-tuning with contextual sparsity.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning SparseloRA: Accelerating LLM fine-tuning with contextual sparsity

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.306225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9200c31e-d192-4cfa-a397-5594ae32d57b · outbound

This paper cites Tr-pts: Task-relevant parameter and token selection for efficient tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Tr-pts: Task-relevant parameter and token selection for efficient tuning

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.335341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3fc3ae67-59d5-45cb-8a10-641ae5e35b2c · outbound

This paper cites AI progress should be measured by capability-per-resource, not scale alone: A framework for gradient-guided resource allocation in LLMs.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning AI progress should be measured by capability-per-resource, not scale alone: A framework for gradient-guided resource allocation in LLMs

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.361819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5526dc4a-c7b2-4805-9601-171a0d585343 · outbound

This paper cites Mitigating forgetting in LLM fine- tuning via low-perplexity token learning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Mitigating forgetting in LLM fine- tuning via low-perplexity token learning

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.428330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 141930e2-7668-4499-bc22-837c63e18056 · outbound

This paper cites On the loss of context awareness in general instruction fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning On the loss of context awareness in general instruction fine-tuning

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.068415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cdc8b943-c92a-4876-895f-bd19b1a6a77d · outbound

This paper cites Mapping post-training forgetting in language models at scale.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Mapping post-training forgetting in language models at scale

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.141890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 45ce195f-8ccb-449d-817a-c62d8be942ad · outbound

This paper cites Don’t make it up: Preserving ignorance awareness in LLM fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Don’t make it up: Preserving ignorance awareness in LLM fine-tuning

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:17.970373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f1e6a252-e3f6-4986-a9b9-50330a5e6f11 · outbound

This paper cites SFT doesn’t always hurt general capa- bilities: Revisiting domain-specific fine-tuning in LLMs.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning SFT doesn’t always hurt general capa- bilities: Revisiting domain-specific fine-tuning in LLMs

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.481331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation be094fb0-7b19-4450-963f-5f609540d75a · outbound

This paper cites Mitigating catastrophic forgetting in large language models with forgetting-aware pruning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Mitigating catastrophic forgetting in large language models with forgetting-aware pruning

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.466746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f1e5faa6-b8f2-4021-8b97-7274fad22695 · outbound

This paper cites Magicoder: Empowering code generation with OSS- instruct.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Magicoder: Empowering code generation with OSS- instruct

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.456019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a1759239-91b2-4e47-84f0-0f50df48186b · outbound

This paper cites Metamath: Bootstrap your own mathematical questions for large language models.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Metamath: Bootstrap your own mathematical questions for large language models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.462759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f60765c9-4e67-499e-ab64-220b92507306 · outbound

This paper cites Lofit: Localized fine-tuning on LLM representations.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Lofit: Localized fine-tuning on LLM representations

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.485019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ddf44ea6-beb2-429c-9c30-f61b3ae30fb7 · outbound

This paper cites Scaling Sparse Fine-Tuning to Large Language Models.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Scaling Sparse Fine-Tuning to Large Language Models

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:51:07.475875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 24d96dbf-87cc-4837-863c-e9f7382093cd · outbound

This paper cites Taso: Task-aligned sparse optimization for parameter-efficient model adaptation.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Taso: Task-aligned sparse optimization for parameter-efficient model adaptation

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.055281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 77785bd3-0de9-4bd4-a6c8-5aac75750fa7 · outbound

This paper cites How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:51:07.467799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cf0213bb-963b-4605-99a1-ce6dd3a2fdce · outbound

This paper cites FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:51:07.433669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0d65d3bc-4124-4f05-a67d-974846160c4f · outbound

This paper cites Hft: Half fine-tuning for large language models.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Hft: Half fine-tuning for large language models

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.129185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fd958bc8-e338-4d5e-a244-a0a3f2145e12 · outbound

This paper cites Recurrent knowledge identification and fusion for language model continual learning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Recurrent knowledge identification and fusion for language model continual learning

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.448847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bdd2db40-f36e-4d1f-9ff2-5b73b9e3afe3 · outbound

This paper cites Parameter importance-driven continual learning for foundation mod- els.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Parameter importance-driven continual learning for foundation mod- els

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:51:07.439079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 704a610b-e652-491c-bff4-5e4dc1b9c35f · outbound

This paper cites MODEL SHAPLEY : Find your ideal parameter player via one gradient backpropagation.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning MODEL SHAPLEY : Find your ideal parameter player via one gradient backpropagation

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.401310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 547beda4-22e7-490d-a40c-3ada6002ce2e · outbound

This paper cites ShaploRA: Allocation of low-rank adaption on large language models via shapley value inspired importance estimation.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning ShaploRA: Allocation of low-rank adaption on large language models via shapley value inspired importance estimation

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.424979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ac16f2d1-6b75-4ece-9d00-b71d98f5b51c · outbound

This paper cites Pruning as a cooperative game: Surrogate- assisted layer contribution estimation for large language models.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Pruning as a cooperative game: Surrogate- assisted layer contribution estimation for large language models

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.441616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 664d7d6e-5e63-4543-8c73-3c69072bd468 · outbound

This paper cites Token cleaning: Fine-grained data selec- tion for LLM supervised fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Token cleaning: Fine-grained data selec- tion for LLM supervised fine-tuning

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.105393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6a2305f5-2579-4852-8bee-0aa35a72dead · outbound

This paper cites Token-level data selection for safe LLM fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Token-level data selection for safe LLM fine-tuning

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.016783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c60a3888-a52e-4ca7-b12d-3a3eb7595901 · outbound

This paper cites sstoken: Self-modulated and semantic-aware token selection for LLM fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning sstoken: Self-modulated and semantic-aware token selection for LLM fine-tuning

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.146252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ed43311e-958f-470f-9d0d-4018a37c5264 · outbound

This paper cites Train on validation (tov): Fast data selection with applications to fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Train on validation (tov): Fast data selection with applications to fine-tuning

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.150704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a35c8257-e2a7-463f-89b5-fb3699fb5a12 · outbound

This paper cites MATES: Model-aware data selection for efficient pretraining with data influence models.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning MATES: Model-aware data selection for efficient pretraining with data influence models

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.093764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 100b065f-b42f-4b0e-a7d5-a852d4882cd7 · outbound

This paper cites Learn more, forget less: A gradient-aware data selection approach for llm.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Learn more, forget less: A gradient-aware data selection approach for llm

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:17.980482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fb3530cb-53af-4d08-ad86-9750c7ede8ac · outbound

This paper cites SEAL: Safety-enhanced aligned LLM fine-tuning via bilevel data selection.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning SEAL: Safety-enhanced aligned LLM fine-tuning via bilevel data selection

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.007633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 097eb2ee-010d-424f-8d75-5f844738eae7 · outbound

This paper cites Data shapley in one training run.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Data shapley in one training run

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.060020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4b50134d-bab6-4827-962a-fc738b48ba7c · outbound

This paper cites CoIDO: Efficient data selection for visual instruc- tion tuning via coupled importance-diversity optimization.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning CoIDO: Efficient data selection for visual instruc- tion tuning via coupled importance-diversity optimization

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.494294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2ea5fccd-3fc7-4d25-94f6-dba7268bd48b · outbound

This paper cites Diversity as a reward: Fine-tuning LLMs on a mixture of domain-undetermined data.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Diversity as a reward: Fine-tuning LLMs on a mixture of domain-undetermined data

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:17.975520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d4273237-892f-4792-bd68-ec8d7300a6c5 · outbound

This paper cites Matched data, better mod- els: Target aligned data filtering with sparse features.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Matched data, better mod- els: Target aligned data filtering with sparse features

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.453170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 588f5f7e-f28c-4e69-ab8d-63c11c7dcb04 · outbound

This paper cites PASER: Post-training data selection for efficient pruned large language model recovery.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning PASER: Post-training data selection for efficient pruned large language model recovery

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.459304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e5425a6e-f33b-455a-80b1-fd5af416f70a · outbound

This paper cites LoRA learns less and forgets less.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning LoRA learns less and forgets less

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.470109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 50c4cfd1-da53-4263-a967-534795f09592 · outbound

This paper cites CorDA: Context-oriented de- composition adaptation of large language models for task-aware parameter-efficient fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning CorDA: Context-oriented de- composition adaptation of large language models for task-aware parameter-efficient fine-tuning

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.503080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 328027ef-afd5-4732-8817-af80f4de9125 · outbound

This paper cites Milora: Harnessing minor singular components for parameter-efficient llm finetuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Milora: Harnessing minor singular components for parameter-efficient llm finetuning

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.410037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eff1649c-5131-41e1-9d26-df72a622f819 · outbound

This paper cites Lora-null: Low-rank adaptation via null space for large language models.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Lora-null: Low-rank adaptation via null space for large language models

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:51:07.479641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4ba5e474-d853-47e0-b550-026b36bcc0e1 · outbound

This paper cites Sc-lora: Balancing efficient fine-tuning and knowledge preservation via subspace-constrained lora.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Sc-lora: Balancing efficient fine-tuning and knowledge preservation via subspace-constrained lora

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:51:07.418727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 59fd743f-008f-45ba-9eeb-28784ab8c2c1 · outbound

This paper cites Slim: Let llm learn more and forget less with soft lora and identity mixture.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Slim: Let llm learn more and forget less with soft lora and identity mixture

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.395573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5b7cfe1d-29c2-4883-b04e-04dd7f48d2ef · outbound

This paper cites MoFO: Momentum-filtered optimizer for mitigating forgetting in LLM fine-tuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning MoFO: Momentum-filtered optimizer for mitigating forgetting in LLM fine-tuning

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.398448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 768ab543-5c36-40fa-b3b9-8a24523e3603 · outbound

This paper cites Loki: Low-damage knowledge implant- ing of large language models.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Loki: Low-damage knowledge implant- ing of large language models

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.415473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 075c408e-1b0d-410c-801f-822c023516dc · outbound

This paper cites Damoc: Efficiently selecting the optimal large language model for fine-tuning domain tasks based on data and model compression.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Damoc: Efficiently selecting the optimal large language model for fine-tuning domain tasks based on data and model compression

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.392509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4311939a-5251-4bd3-8f82-510b6a0e0b04 · outbound

This paper cites Model-agnostic meta-learning for fast adaptation of deep networks.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Model-agnostic meta-learning for fast adaptation of deep networks

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.371219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 38c1c205-d7ae-4d77-b003-9cdc6f972571 · outbound

This paper cites Bilevel programming for hyperparameter optimization and meta-learning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Bilevel programming for hyperparameter optimization and meta-learning

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.374659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 01cc9b07-0724-4221-90b7-b6e6479d074b · outbound

This paper cites DARTS: Differentiable architecture search.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning DARTS: Differentiable architecture search

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.378357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3e209921-3188-4945-a222-1e84e4edfa0d · outbound

This paper cites Glister: Generalization based data subset selection for efficient and robust learning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Glister: Generalization based data subset selection for efficient and robust learning

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.382428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c938db5e-2b96-47cf-a2d3-b9268e6f1a81 · outbound

This paper cites LLM data selection and utilization via dynamic bi-level optimization.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning LLM data selection and utilization via dynamic bi-level optimization

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.364659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 89c984ae-a3dc-4b76-8f4b-48bab8fa9057 · outbound

This paper cites Compress large language models via collaboration between learning and matrix approximation.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Compress large language models via collaboration between learning and matrix approximation

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.367995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3240c1a6-0205-47c6-874f-797f6c4994e9 · outbound

This paper cites Bilevel ZOFO: Efficient LLM fine-tuning and meta- training.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Bilevel ZOFO: Efficient LLM fine-tuning and meta- training

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.388809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ba6e66a9-4c61-4a08-8822-66b784a1008f · outbound

This paper cites Beyond value functions: Single-loop bilevel optimization under flatness conditions.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Beyond value functions: Single-loop bilevel optimization under flatness conditions

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.406254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 89184c7e-5b1f-420f-9806-4154ac5dcc6b · outbound

This paper cites GREATS: Online selection of high-quality data for LLM training in every iteration.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning GREATS: Online selection of high-quality data for LLM training in every iteration

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.445491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0a47be6f-99d6-4e16-811f-f0f1cee48a3f · outbound

This paper cites Influence-preserving proxies for gradient-based data selection in LLM finetuning.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Influence-preserving proxies for gradient-based data selection in LLM finetuning

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.350561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 98a91caf-59f4-4a4b-a4a0-c7319757e690 · outbound

This paper cites Efficient data selection at scale via influence distillation.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Efficient data selection at scale via influence distillation

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.012253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0a1d56dd-7cdf-438d-a758-f5c16de16fee · outbound

This paper cites Group-level data selection for efficient pretraining.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Group-level data selection for efficient pretraining

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.356187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b2ec0ca6-d1b4-431b-a1b8-d0ef922dd963 · outbound

This paper cites Second-order fine-tuning without pain for LLMs: A hessian informed zeroth-order optimizer.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Second-order fine-tuning without pain for LLMs: A hessian informed zeroth-order optimizer

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.436816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 58959dfb-7aed-4131-82ec-085a68045a02 · outbound

This paper cites PaZO: Preconditioned accelerated zeroth-order optimization for fine-tuning LLMs.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning PaZO: Preconditioned accelerated zeroth-order optimization for fine-tuning LLMs

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.474171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3aae9b97-c520-4ae5-95f8-3dc926efb80b · outbound

This paper cites Helene: Hessian layer-wise clipping and gradient annealing for accelerating fine-tuning llm with zeroth-order optimization.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Helene: Hessian layer-wise clipping and gradient annealing for accelerating fine-tuning llm with zeroth-order optimization

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.512215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e61b6762-ca3f-47ef-814c-719820cd7053 · outbound

This paper cites Mitigating forgetting in low rank adap- tation.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Mitigating forgetting in low rank adap- tation

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.025638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 04ae0284-ac76-4d44-b6cc-2d7a9485a945 · outbound

This paper cites Adam-mini: Use fewer learning rates to gain more.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Adam-mini: Use fewer learning rates to gain more

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:12:18.432811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a245aee7-78e0-4b88-8f34-136eb1a2a1b1 · outbound

This paper cites When can you get away with low memory adam?.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning When can you get away with low memory adam?

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.089561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b65fe672-dab5-4161-9207-3b456fe89c4e · outbound

This paper cites Adaptive Preconditioners Trigger Loss Spikes in Adam.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning Adaptive Preconditioners Trigger Loss Spikes in Adam

Reference 98

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:02.571868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b7204905-68dc-408a-ad0d-b7bbad10b481 · outbound

This paper cites LDAdam: Adaptive optimization from low- dimensional gradient statistics.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning LDAdam: Adaptive optimization from low- dimensional gradient statistics

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.077273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 041a49ce-38d0-4f13-b300-39b698006f44 · outbound

This paper cites SOAP: Improving and stabilizing shampoo using adam for language modeling.

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning SOAP: Improving and stabilizing shampoo using adam for language modeling

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T12:17:18.046528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers