mlsanityData to 7 Oct 2026

ADELIE: Aligning Large Language Models on Information Extraction

arXiv 2405.05008 ↗First posted 8 May 2024cs.CLcited by 24

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

Large language models (LLMs) usually fall short on information extraction (IE) tasks and struggle to follow the complex instructions of IE tasks. This primarily arises from LLMs not being aligned with humans, as mainstream alignment datasets typically do not include IE data. In this paper, we introduce ADELIE (Aligning large language moDELs on Information Extraction), an aligned LLM that effectively solves various IE tasks, including closed IE, open IE, and on-demand IE. We first collect and construct a high-quality alignment corpus IEInstruct for IE. Then we train ADELIE_SFT using instruction tuning on IEInstruct. We further train ADELIE_SFT with direct preference optimization (DPO) objective, resulting in ADELIE_DPO. Extensive experiments on various held-out IE datasets demonstrate that our models (ADELIE_SFT and ADELIE_DPO) achieve state-of-the-art (SoTA) performance among open-source models. We further explore the general capabilities of ADELIE, and experimental results reveal that their general capabilities do not exhibit a noticeable decline. We will release the code, data, and models to facilitate further research.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 42 of its 70 references that are in the map. First posted on arXiv 8 May 2024.

Builds on

42 of 70 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Aligning Large Language Models through Synthetic Feedback23 May
  2. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructions20 Dec
  3. 2022Training language models to follow instructions with human feedback4 Mar

Other references · 39

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  4. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  6. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  7. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  8. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  9. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  10. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  11. 2022Large Language Models Can Self-Improvecited by 656
  12. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
27 more
  1. 2018Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Constructioncited by 321
  2. 2024Long-context LLMs Struggle with Long In-context Learningcited by 285
  3. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  4. 2023ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPTcited by 250
  5. 2022Unified Structure Generation for Universal Information Extractioncited by 220
  6. 2023Large Language Models for Generative Information Extraction: A Surveycited by 183
  7. 2023InstructUIE: Multi-task Instruction Tuning for Unified Information Extractioncited by 167
  8. 2021Document-Level Event Argument Extraction by Conditional Generationcited by 154
  9. 2021Few-NERD: A Few-Shot Named Entity Recognition Datasetcited by 150
  10. 2023Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulnesscited by 130
  11. 2019A Survey on Recent Advances in Named Entity Recognition from Deep Learning modelscited by 117
  12. 2023GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extractioncited by 116
  13. 2020MAVEN: A Massive General Domain Event Detection Datasetcited by 103
  14. 2018A Multi-Axis Annotation Scheme for Event Temporal Relationscited by 73
  15. 2023Symbol tuning improves in-context learning in language modelscited by 72
  16. 2022Code4Struct: Code Generation for Few-Shot Event Structure Predictioncited by 70
  17. 2023CodeIE: Large Code Generation Models are Better Few-Shot Information Extractorscited by 67
  18. 2022MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extractioncited by 65
  19. 2020More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extractioncited by 52
  20. 2018A Hierarchical Framework for Relation Extraction with Reinforcement Learningcited by 49
  21. 2023Retrieval-Augmented Code Generation for Universal Information Extractioncited by 40
  22. 2023When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Taskscited by 37
  23. 2022PHEE: A Dataset for Pharmacovigilance Event Extraction from Textcited by 36
  24. 2023Instruct and Extract: Instruction Tuning for On-Demand Information Extractioncited by 35
  25. 2023Guideline Learning for In-context Information Extractioncited by 24
  26. 2023The Devil is in the Details: On the Pitfalls of Event Extraction Evaluationcited by 18
  27. 2023One Model for All Domains: Collaborative Domain-Prefix Tuning for Cross-Domain NERcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 10; 2026: 9.

24 papers.

Sort:

By area:

  1. 2024Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neuronscited by 47
  2. 2024Pre-training Distillation for Large Language Models: A Design Space Explorationcited by 25
  3. 2024Constraint Back-translation Improves Complex Instruction Following of Large Language Modelscited by 11
  4. 2025Iterative Self-Incentivization Empowers Large Language Models as Agentic Searcherscited by 11
  5. 2024MAVEN-Fact: A Large-scale Event Factuality Detection Datasetcited by 6
  6. 2024Towards Better Multi-task Learning: A Framework for Optimizing Dataset Combinations in Large Language Modelscited by 6
  7. 2025MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extractioncited by 6
  8. 2025Event Extraction in Large Language Modelcited by 5
  9. 2025GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extractioncited by 3
  10. 2025Benchmarking and Improving LVLMs on Event Extraction from Multimedia Documentscited by 3
  11. 2025Schema as Parameterized Tools for Universal Information Extractioncited by 2
  12. 2025Selecting and Merging: Towards Adaptable and Scalable Named Entity Recognition with Large Language Modelscited by 2
12 more
  1. 2025Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesiscited by 1
  2. 2025Zero-Shot Open-Schema Entity Structure Discoverycited by 1
  3. 2026ExStrucTiny: A Benchmark for Schema-Variable Structured Information Extraction from Document Imagescited by 1
  4. 2025The Answer Lies Within: Self-Derived Rewards Enable Explainable Relation Extractioncited by 0
  5. 2026Sensory-Aware Sequential Recommendation via Review-Distilled Representationscited by 0
  6. 2026LiveWeb-IE: A Benchmark For Online Web Information Extractioncited by 0
  7. 2026Code-MIE: A Code-style Model for Multimodal Information Extraction with Scene Graph and Entity Attribute Knowledge Enhancementcited by 0
  8. 2026DiZiNER: Disagreement-guided Instruction Refinement via Pilot Annotation Simulation for Zero-shot Named Entity Recognitioncited by 0
  9. 2026BoostTaxo: Zero-Shot Taxonomy Induction via Boosting-Style Agentic Reasoning and Constraint-Aware Calibrationcited by 0
  10. 2026CMNIE: An Information Extraction Benchmark for Chinese Military Newscited by 0
  11. 2026TEAR: Table Extraction with Attribute Recommendation from Texts via Large Language Modelscited by 0
  12. 2026EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewardscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Efficient and Effective Alignment of Large Language Models
  2. 2025InfoPO: On Mutual Information Maximization for Large Language Model Alignment
  3. 2024Efficient Alignment of Large Language Models via Data Sampling
  4. 2025Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples
  5. 2024Aligner: Efficient Alignment by Learning to Correct
  6. 2025Data Selection for LLM Alignment Using Fine-Grained Preferences
  7. 2025A Survey on Training-free Alignment of Large Language Models
  8. 2023Aligning Large Language Models with Human: A Survey