Delta Activations: A Representation for Finetuned Large Language Models | Paper Citation Record

Observation 2f4667fe-cbd5-450e-8c98-ab69438596ae · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Delta Activations: A Representation for Finetuned Large Language Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.326787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbbdc1fc-9052-4a6c-a523-22e9c47890c6 · outbound

This paper cites Perception Encoder: The best visual embeddings are not at the output of the network.

Delta Activations: A Representation for Finetuned Large Language Models Perception Encoder: The best visual embeddings are not at the output of the network

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.332092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85ba4053-dc85-474f-a29d-f2314f8a839f · outbound

This paper cites Enhancing human-like responses in large language models.

Delta Activations: A Representation for Finetuned Large Language Models Enhancing human-like responses in large language models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.336854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef339b14-508c-43cc-aff7-92f3a3526fd3 · outbound

This paper cites Generative pretraining from pixels.

Delta Activations: A Representation for Finetuned Large Language Models Generative pretraining from pixels

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.341255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 103fc2b6-d3b6-4e14-bfc8-3c736bf3d243 · outbound

This paper cites Adaptersoup: Weight averaging to improve generalization of pretrained language models.

Delta Activations: A Representation for Finetuned Large Language Models Adaptersoup: Weight averaging to improve generalization of pretrained language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.890691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7a65f817-513d-4635-b971-c4ceb0a87557 · outbound

This paper cites Scaling instruction-finetuned language models.

Delta Activations: A Representation for Finetuned Large Language Models Scaling instruction-finetuned language models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.350142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a214009-9319-4d2d-838e-e79341a5be54 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Delta Activations: A Representation for Finetuned Large Language Models Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.354917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88217135-2979-4a86-8f86-2312ab3cb586 · outbound

This paper cites Codechef.

Delta Activations: A Representation for Finetuned Large Language Models Codechef

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.867269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 40e078ae-b32c-4d76-8e5f-746b0911c37d · outbound

This paper cites Ultrafeedback: Boosting language models with scaled ai feedback.

Delta Activations: A Representation for Finetuned Large Language Models Ultrafeedback: Boosting language models with scaled ai feedback

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.852185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4b39f0e9-3da5-43e5-8661-1a7664750141 · outbound

This paper cites an unresolved cited work.

Delta Activations: A Representation for Finetuned Large Language Models Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:32:09.838334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8a232189-12cc-4b03-846e-d887461aa1be · outbound

This paper cites Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence.

Delta Activations: A Representation for Finetuned Large Language Models Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.371617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d81e97f-b9ff-4ff1-b7bf-ee80371cb1ec · outbound

This paper cites Sparsegpt: Massive language models can be accurately pruned in one-shot.

Delta Activations: A Representation for Finetuned Large Language Models Sparsegpt: Massive language models can be accurately pruned in one-shot

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.824212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 40cf88de-adbe-44b3-a468-0652ef7f363b · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Delta Activations: A Representation for Finetuned Large Language Models GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.380374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79cd76d8-d8a9-4092-af0f-41d120ae7935 · outbound

This paper cites Disease database.

Delta Activations: A Representation for Finetuned Large Language Models Disease database

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.810103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 45f14e64-2201-4c9d-abcc-a58ea9ea8732 · outbound

This paper cites Ho, Christopher Ré, Adam Chilton, Aditya Narayana, Alex Chohlas-Wood, Austin Peters, Brandon Waldon, Daniel N.

Delta Activations: A Representation for Finetuned Large Language Models Ho, Christopher Ré, Adam Chilton, Aditya Narayana, Alex Chohlas-Wood, Austin Peters, Brandon Waldon, Daniel N

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.796232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 058b5a87-3a64-40e3-b91a-0c0ecb485b98 · outbound

This paper cites Learning both weights and connections for efficient neural network.

Delta Activations: A Representation for Finetuned Large Language Models Learning both weights and connections for efficient neural network

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.393946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcadcba2-b785-485a-94d5-7cad33af0f78 · outbound

This paper cites Localize-and-stitch: Efficient model merging via sparse task arithmetic.

Delta Activations: A Representation for Finetuned Large Language Models Localize-and-stitch: Efficient model merging via sparse task arithmetic

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.773205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bf8ee774-0c1a-47c8-9abe-f3dd6816d619 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Delta Activations: A Representation for Finetuned Large Language Models Distilling the Knowledge in a Neural Network

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.407268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aaf1dfe-d83d-4a1d-adce-e9738382bcc7 · outbound

This paper cites Unsupervised model tree heritage recovery.

Delta Activations: A Representation for Finetuned Large Language Models Unsupervised model tree heritage recovery

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.759210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8b99698b-2284-4a12-9202-7edcd3003de9 · outbound

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

Delta Activations: A Representation for Finetuned Large Language Models LoRA: Low-rank adaptation of large language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.744848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4df1b9f8-4841-40ce-b2f0-6ac381bb15a3 · outbound

This paper cites Lorahub: Efficient cross-task generalization via dynamic lora composition.

Delta Activations: A Representation for Finetuned Large Language Models Lorahub: Efficient cross-task generalization via dynamic lora composition

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.731020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5d3eeda6-59f2-4d26-a667-22743893c41c · outbound

This paper cites OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models.

Delta Activations: A Representation for Finetuned Large Language Models OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.425003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd5cf55f-705e-4688-bbe0-9ae92c7beca3 · outbound

This paper cites Editing models with task arithmetic.

Delta Activations: A Representation for Finetuned Large Language Models Editing models with task arithmetic

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.429527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97c68dbb-ad45-48bf-af93-924398f89534 · outbound

This paper cites Smith, Iz Beltagy, and Hannaneh Hajishirzi.

Delta Activations: A Representation for Finetuned Large Language Models Smith, Iz Beltagy, and Hannaneh Hajishirzi

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.433897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c08e668-2958-474e-be54-e19c230e8a63 · outbound

This paper cites What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams.

Delta Activations: A Representation for Finetuned Large Language Models What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.438305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7de531df-fd8c-40a9-8583-481b25b7f32f · outbound

This paper cites Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection.

Delta Activations: A Representation for Finetuned Large Language Models Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.442640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abd7b20f-c076-4508-bd8f-60945a17ccaa · outbound

This paper cites Pubmedqa: A dataset for biomedical research question answering.

Delta Activations: A Representation for Finetuned Large Language Models Pubmedqa: A dataset for biomedical research question answering

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.699069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 21d24ba5-9b6c-49c8-9270-cd057cc2cea5 · outbound

This paper cites Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights.

Delta Activations: A Representation for Finetuned Large Language Models Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-15T16:32:09.081140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d9f6495d-7cbf-484f-a94e-e8b786c7ef60 · outbound

This paper cites Matrix factorization techniques for recom- mender systems.

Delta Activations: A Representation for Finetuned Large Language Models Matrix factorization techniques for recom- mender systems

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.684729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d2200470-eb60-42df-a646-0614ce372239 · outbound

This paper cites Imagenet classification with deep convolutional neural networks.

Delta Activations: A Representation for Finetuned Large Language Models Imagenet classification with deep convolutional neural networks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.460048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56fa0e4b-eb23-4138-8336-a6208c34759b · outbound

This paper cites Optimal brain damage.

Delta Activations: A Representation for Finetuned Large Language Models Optimal brain damage

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.661802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5e4b4bdf-3d82-41bf-9b83-cee07dd69f4a · outbound

This paper cites Emergent world representations: Exploring a sequence model trained on a synthetic task.

Delta Activations: A Representation for Finetuned Large Language Models Emergent world representations: Exploring a sequence model trained on a synthetic task

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.648159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d0fd2b36-02e9-4f42-89e1-6332c152a6fc · outbound

This paper cites Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights.

Delta Activations: A Representation for Finetuned Large Language Models Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.472785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e697722f-4f9c-4a48-88d2-0b46d2c7b0d4 · outbound

This paper cites Awq: Activation- aware weight quantization for llm compression and acceleration.

Delta Activations: A Representation for Finetuned Large Language Models Awq: Activation- aware weight quantization for llm compression and acceleration

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.633968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a05aabf2-6932-44cf-be7b-eb98458e5c7a · outbound

This paper cites DeepSeek-V3 Technical Report.

Delta Activations: A Representation for Finetuned Large Language Models DeepSeek-V3 Technical Report

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.480927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce154081-bdbc-45c6-8b3a-7996c2f6abac · outbound

This paper cites In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering.

Delta Activations: A Representation for Finetuned Large Language Models In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.484913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce5abddd-742b-406c-8ed1-7c1aa05cf406 · outbound

This paper cites Meaning representations from trajectories in autoregressive models.

Delta Activations: A Representation for Finetuned Large Language Models Meaning representations from trajectories in autoregressive models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.618085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ae5693ab-bf8d-47bc-8061-c5e136422c6f · outbound

This paper cites Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models.

Delta Activations: A Representation for Finetuned Large Language Models Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.493334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f82f3d1b-e34b-4ad7-8f0f-d6ff837b66b7 · outbound

This paper cites Pace: Parsimonious concept engineering for large language models.

Delta Activations: A Representation for Finetuned Large Language Models Pace: Parsimonious concept engineering for large language models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.604348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8e882392-0f75-4417-af43-a192cca6f1f6 · outbound

This paper cites Stylus: Automatic adapter selection for diffusion models.

Delta Activations: A Representation for Finetuned Large Language Models Stylus: Automatic adapter selection for diffusion models

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.590240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ef9b7756-555a-459a-85c9-5d449adb242a · outbound

This paper cites Wizardcoder: Empowering code large language models with evol-instruct.

Delta Activations: A Representation for Finetuned Large Language Models Wizardcoder: Empowering code large language models with evol-instruct

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.575934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c0abb847-84b7-42ad-ae3f-e23a0f6b2bfe · outbound

This paper cites Simpo: Simple preference optimization with a reference-free reward.

Delta Activations: A Representation for Finetuned Large Language Models Simpo: Simple preference optimization with a reference-free reward

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.562331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 825e2cbe-c86f-4d94-817f-00874ac8685c · outbound

This paper cites Efficient estimation of word representations in vector space.

Delta Activations: A Representation for Finetuned Large Language Models Efficient estimation of word representations in vector space

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.514380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22527f98-3d4b-431c-9872-d979dc3f7975 · outbound

This paper cites Disease-symptoms dataset.

Delta Activations: A Representation for Finetuned Large Language Models Disease-symptoms dataset

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.538740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation de136e09-f7bd-47a6-8606-0ce3b6abd8da · outbound

This paper cites SGPT: GPT Sentence Embeddings for Semantic Search.

Delta Activations: A Representation for Finetuned Large Language Models SGPT: GPT Sentence Embeddings for Semantic Search

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.522684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78732b8c-377a-44c2-bb1f-c6e582be91ea · outbound

This paper cites Routellm: Learning to route llms from preference data.

Delta Activations: A Representation for Finetuned Large Language Models Routellm: Learning to route llms from preference data

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.525334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c88b61ed-88ec-4e9a-982b-8301aea5817a · outbound

This paper cites Task arithmetic in the tangent space: Improved editing of pre-trained models.

Delta Activations: A Representation for Finetuned Large Language Models Task arithmetic in the tangent space: Improved editing of pre-trained models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.511531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4f33eaa1-5338-4145-9c2b-c29133b949d0 · outbound

This paper cites Towards Modular LLMs by Building and Reusing a Library of LoRAs.

Delta Activations: A Representation for Finetuned Large Language Models Towards Modular LLMs by Building and Reusing a Library of LoRAs

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.535235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation beba2ccf-d853-47d9-a515-da3f027392da · outbound

This paper cites Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering.

Delta Activations: A Representation for Finetuned Large Language Models Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.498028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ed173306-e3e8-4af7-bfda-4637053cc9a7 · outbound

This paper cites Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive.

Delta Activations: A Representation for Finetuned Large Language Models Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.544692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff297c72-da6e-463f-a144-ec7dcb3b1354 · outbound

This paper cites Codeelo: Benchmarking competition-level code generation of llms with human-comparable elo ratings, 2025.

Delta Activations: A Representation for Finetuned Large Language Models Codeelo: Benchmarking competition-level code generation of llms with human-comparable elo ratings, 2025

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.483941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1092fb62-c34c-4806-b5e9-922da93f5c91 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Delta Activations: A Representation for Finetuned Large Language Models Direct preference optimization: Your language model is secretly a reward model

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.554290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a0fe00b-5ea6-4641-b447-95617544dd91 · outbound

This paper cites Learning dynamics of llm finetuning.

Delta Activations: A Representation for Finetuned Large Language Models Learning dynamics of llm finetuning

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.461371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation dd49da10-e15c-4f8c-9d2b-3314efead1af · outbound

This paper cites Rousseeuw.

Delta Activations: A Representation for Finetuned Large Language Models Rousseeuw

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.447940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c9ac31a0-0410-4bcd-8bd4-0b886abd2d9a · outbound

This paper cites Large Language Model Routing with Benchmark Datasets.

Delta Activations: A Representation for Finetuned Large Language Models Large Language Model Routing with Benchmark Datasets

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.566431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d1a504b-24f4-459d-9166-83d3ba24739f · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

Delta Activations: A Representation for Finetuned Large Language Models A Simple and Effective Pruning Approach for Large Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.570501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a5b33fa-4054-4e01-8a5e-9fea87d3e9f5 · outbound

This paper cites Zico Kolter, and Zhuang Liu.

Delta Activations: A Representation for Finetuned Large Language Models Zico Kolter, and Zhuang Liu

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.434281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2084aa51-711c-4a44-acc1-18411fef60f4 · outbound

This paper cites Zico Kolter, and Zhuang Liu.

Delta Activations: A Representation for Finetuned Large Language Models Zico Kolter, and Zhuang Liu

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.420106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0aa7a8ed-d2e5-4870-9029-3e490557caaf · outbound

This paper cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.

Delta Activations: A Representation for Finetuned Large Language Models Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.584823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 980c1259-a3e7-42dd-a11d-9415d4f9b4f8 · outbound

This paper cites Learnware of Language Models: Specialized Small Language Models Can Do Big.

Delta Activations: A Representation for Finetuned Large Language Models Learnware of Language Models: Specialized Small Language Models Can Do Big

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-08-15T16:32:08.918648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1c0b89ae-be85-41f1-b4eb-70b0b0fa06e7 · outbound

This paper cites Alpaca: A strong, replicable instruction-following model.

Delta Activations: A Representation for Finetuned Large Language Models Alpaca: A strong, replicable instruction-following model

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.404220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e1209b46-6d8c-48a4-b368-8ccbe7bfd953 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Delta Activations: A Representation for Finetuned Large Language Models Gemma 2: Improving Open Language Models at a Practical Size

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.597650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ea137ba-0a3e-4836-aa5f-d5d17b28602e · outbound

This paper cites Contrastive Representation Distillation.

Delta Activations: A Representation for Finetuned Large Language Models Contrastive Representation Distillation

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.601956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af525828-1da8-4852-bd34-63d2f2e8accb · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Delta Activations: A Representation for Finetuned Large Language Models LLaMA: Open and Efficient Foundation Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.606212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbd2046c-fcc5-47ef-b859-5c1b65515298 · outbound

This paper cites Neural Network Diffusion.

Delta Activations: A Representation for Finetuned Large Language Models Neural Network Diffusion

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.610494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 997cd79a-81f1-4fd5-acd4-833db2647dec · outbound

This paper cites MiniLMv2: Multi-head self-attention relation distillation for compressing pretrained transformers.

Delta Activations: A Representation for Finetuned Large Language Models MiniLMv2: Multi-head self-attention relation distillation for compressing pretrained transformers

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.390108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c0701a2d-42d7-40fb-abdb-45794ab56043 · outbound

This paper cites Sheared LLaMA: Accelerating language model pre-training via structured pruning.

Delta Activations: A Representation for Finetuned Large Language Models Sheared LLaMA: Accelerating language model pre-training via structured pruning

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.376285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0a29b9f2-0308-485b-bbe3-8c0b99fbc3a2 · outbound

This paper cites Initializing models with larger ones.

Delta Activations: A Representation for Finetuned Large Language Models Initializing models with larger ones

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.362416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c4b3b5ee-60db-4356-847a-62242e709901 · outbound

This paper cites Qwen2.5 Technical Report.

Delta Activations: A Representation for Finetuned Large Language Models Qwen2.5 Technical Report

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.627457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34718942-5f39-4802-882d-e39c908bc14d · outbound

This paper cites Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities.

Delta Activations: A Representation for Finetuned Large Language Models Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.631926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0f43d3f-f8d2-42ae-ae1f-deaa3e0bce1e · outbound

This paper cites Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity.

Delta Activations: A Representation for Finetuned Large Language Models Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.636003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5cc9eae-0f07-44b2-9666-b252b5a93390 · outbound

This paper cites MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models.

Delta Activations: A Representation for Finetuned Large Language Models MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.640819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4c40920-7fc8-4c64-b645-9b5cc6bf667a · outbound

This paper cites Neural phylogeny: Fine-tuning relationship detection among neural networks.

Delta Activations: A Representation for Finetuned Large Language Models Neural phylogeny: Fine-tuning relationship detection among neural networks

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.348637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c99d9f80-d600-4cc1-a359-c8286a16875a · outbound

This paper cites Hellaswag: Can a machine really finish your sentence? In ACL, 2019.

Delta Activations: A Representation for Finetuned Large Language Models Hellaswag: Can a machine really finish your sentence? In ACL, 2019

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.649880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b19375b8-802d-42cb-b111-a713d1f36f17 · outbound

This paper cites Generative modeling of weights: General- ization or memorization? arXiv preprint arXiv:2506.07998, 2025.

Delta Activations: A Representation for Finetuned Large Language Models Generative modeling of weights: General- ization or memorization? arXiv preprint arXiv:2506.07998, 2025

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.653768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e7bf94e-0a31-4c96-be21-cd49f0a0b0c6 · outbound

This paper cites Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs.

Delta Activations: A Representation for Finetuned Large Language Models Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.658364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 665fce63-c13c-40fc-8b1e-475cb3461df3 · outbound

This paper cites LoraRetriever: Input-aware LoRA retrieval and composition for mixed tasks in the wild.

Delta Activations: A Representation for Finetuned Large Language Models LoraRetriever: Input-aware LoRA retrieval and composition for mixed tasks in the wild

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.325568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0955bc0e-d9e7-4d4a-96fb-5e4033538886 · outbound

This paper cites A comprehensive survey on transfer learning.

Delta Activations: A Representation for Finetuned Large Language Models A comprehensive survey on transfer learning

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.666511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dcf9caf-dcfb-4b9a-b2d9-25c4dc8772dc · outbound

This paper cites meaning vector.

Delta Activations: A Representation for Finetuned Large Language Models meaning vector

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:32:09.302295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 46bd37af-6871-411d-8ce7-82d95270512e · outbound

This paper cites Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic.

Delta Activations: A Representation for Finetuned Large Language Models Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T16:32:08.402542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers