Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-12T18:51:32.098357Z
Paper Citation Record · LEDGER
As of 21 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 1 inbound Pith citation observation for arXiv:2411.11266.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-12T18:51:32.098357Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-07T14:00:31.489767Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-07T14:00:34.048977Z
70 of 70 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation bd819cda-105b-4f6e-a467-f1226c41c40b · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs GPT-4 Technical Report
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 66e539f8-e050-4dfd-a346-93b238b12de6 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs A Survey on Data Selection for Language Models
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2adb10e4-df51-42b0-be2d-6c848ef79494 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 3
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 f4666535-99b4-407c-adfa-d15ec3f23a44 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9f841abd-3143-4ba3-9f81-cc7f1de760fd · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Program Synthesis with Large Language Models
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 253463bb-d851-488d-ac8a-6c4997d6185d · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Llemma: An Open Language Model For Mathematics
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 088586a5-4b62-44ae-956a-ce06b3a6715e · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Qwen Technical Report
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 86a18418-fb82-412c-ac11-5c5dd432d218 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs SciBERT: A Pretrained Language Model for Scientific Text
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 14148b0f-0f4c-4a42-a09f-67984d8e255b · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bfab9d93-f48b-41a1-ab8d-905716db9558 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 10
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 086cb86e-d891-4695-9133-0741539e2e38 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Evaluating Large Language Models Trained on Code
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 97c24247-648e-4eab-a0d0-4242ced453fb · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a07b13f6-3424-4d33-8009-2dca0cd4c23c · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7f7d6132-d783-4f19-8d39-e7e1c8df4fc3 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b9538de6-0a1b-414b-91b7-4cbf4b143c81 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5c3f702f-8878-4895-9d94-ee37ac92c679 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8f25e9d2-72b5-486f-8f7b-89c5f060048e · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs The Llama 3 Herd of Models
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dcc45ee9-9b5b-4d72-b15b-5613168cdd2a · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 18
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 33c63d39-ccb8-4aa1-b181-eb86a6eb7e20 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs DoGE: Domain Reweighting with Generalization Estimation
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d7441a82-5522-403c-bc12-85365300c0d6 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs LawBench: Benchmarking Legal Knowledge of Large Language Models
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c00d3641-0e0e-4fbb-9cc9-07366f6a8ec5 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation de8d1c57-4b74-4ba1-ba86-e69e8a8bf280 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fbace07d-c268-44ca-8942-4164bdf7ec8f · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 636f10e2-c638-484d-b65a-022bbc0ed71f · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Measuring Massive Multitask Language Understanding
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7c82a31c-5dca-46f1-a78a-a1638dc216d4 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3652586c-44c9-4d4d-88f6-54f706de163e · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs GPT-4o System Card
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 06855ddf-ec89-4283-b024-6d8b02d5f232 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ef2049a0-4d53-42d0-9fe8-c6a100ae44a3 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Language Models (Mostly) Know What They Know
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dc182685-f217-49c0-923b-cac8bfe1bd4b · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6f253472-b4f3-4aae-952a-edb82b1fa35d · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bded5c70-439f-4371-b820-00fa88ed94ee · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 70d30b1f-f86c-45b8-a222-890b287ecd78 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 32
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 d6370541-6ffd-4732-bf63-181051e727d0 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 46282825-feb2-4081-8fd5-c4cddec069c2 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs DeepSeek-V3 Technical Report
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d9ce1c14-a018-4843-87ce-495786a71edd · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b4be350c-8f36-4a3d-97e8-c41bd4197ff8 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 54013563-3b1a-442c-9066-e47e5b14754f · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 37
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7cfbec12-0c56-420a-82b9-0a475dea090f · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 38
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 649013ea-c70d-4906-a563-326cf5712d91 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 39
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6471e017-3a83-4f37-b7b9-48fbcab358cf · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 40
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f472b5d4-1999-451a-9040-d657bf852cc5 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Code Llama: Open Foundation Models for Code
Reference 41
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c8cd4085-8ce0-4ebe-84de-aa7d092e30d1 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Multitask Prompted Training Enables Zero-Shot Task Generalization
Reference 42
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 219bc52d-a49d-4343-8fcc-c02e5dc2ac96 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 43
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5257fc2b-95f2-4ff4-80ed-208fa23fcb28 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 44
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 77dc1435-7aaf-4600-b4f2-bd70f16c3f60 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 45
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2b44a643-45e2-499f-b807-1f0c302293c2 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Galactica: A Large Language Model for Science
Reference 46
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 35d1db4d-46e5-41d3-8894-163a707afe1b · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Gemini: A Family of Highly Capable Multimodal Models
Reference 47
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 511daa67-239d-4a84-9a98-8a7f43fafb5b · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 48
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b29e1448-7e2c-492f-abd5-f29957788432 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs LLaMA: Open and Efficient Foundation Language Models
Reference 49
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e0c356fe-de23-48bd-b2a9-550de82a0bfc · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 50
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 416aedf5-fa2f-4434-82df-92c346517dbd · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Smith, Daniel Khashabi, and Hannaneh Hajishirzi
Reference 51
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 135f5adc-86ac-4866-8efd-2441402ee07f · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Data Management For Training Large Language Models: A Survey
Reference 52
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9fb7865a-73ea-40e3-b8fe-1d4189a722b4 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 53
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 1f38d0bf-4bd2-4854-aedc-89838b7ef7f3 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs BloombergGPT: A Large Language Model for Finance
Reference 54
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 25bf0933-7ebc-465f-a7fb-dfe8cb9c3064 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
Reference 55
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7d27460d-a6fa-492c-b676-19855c405379 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs FinBen: A Holistic Financial Benchmark for Large Language Models
Reference 56
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a6a1984a-f998-4f6a-9a6e-9093f9324d7c · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 57
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 a0954c00-72ca-4b18-ab21-db6ea88ecfef · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 58
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 adf89d80-f987-4b37-9250-7348b7b5d3ad · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Qwen2 Technical Report
Reference 59
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 03a558a2-414a-4702-b09e-3a66c94093fe · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 60
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 e64d8ed5-eba6-46f2-b676-cfb25cf79b0a · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation
Reference 61
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 db8947d3-7676-4658-bfac-944f5d5855c6 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs HellaSwag: Can a Machine Really Finish Your Sentence?
Reference 62
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 343e5d56-76eb-4718-b144-589d398aebd5 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
Reference 63
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 87159dc8-6665-4f18-95bc-02f37debd5d9 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models
Reference 64
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4a18309e-b64f-4b0b-a454-7f6a08a15c28 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Unresolved cited work
Reference 65
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 3a1dc180-dea3-43d4-9ece-9ec03af1eaa3 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs A Survey of Large Language Models
Reference 66
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d9a6b5cd-770f-4267-9887-ec304e8f23cb · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method
Reference 67
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 647feef1-e139-46ad-a26a-5c623538ab62 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models
Reference 68
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3fa1892e-a29f-4298-8d19-669ed792b295 · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs online" 'onlinestring :=
Reference 69
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation af8b5b03-435b-4a10-a539-ed85f990b9af · outbound
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs write newline
Reference 70
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8057caba-38b6-4025-b1b0-9f71da005ca1 · inbound
GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs
Reference 23
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.