mlsanityData to 14 Oct 2026

GIER: Gap-Driven Self-Refinement for Large Language Models

arXiv 2509.00325 ↗First posted 30 Aug 2025cs.CL cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce GIER (Gap-driven Iterative Enhancement of Responses), a general framework for improving large language model (LLM) outputs through self-reflection and revision based on conceptual quality criteria. Unlike prompting strategies that rely on demonstrations, examples, or chain-of-thought templates, GIER utilizes natural language descriptions of reasoning gaps, and prompts a model to iteratively critique and refine its own outputs to better satisfy these criteria. Across three reasoning-intensive tasks (SciFact, PrivacyQA, and e-SNLI) and four LLMs (GPT-4.1, GPT-4o Mini, Gemini 1.5 Pro, and Llama 3.3 70B), GIER improves rationale quality, grounding, and reasoning alignment without degrading task accuracy. Our analysis demonstrates that models can not only interpret abstract conceptual gaps but also translate them into concrete reasoning improvements.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 39 references that are in the map. First posted on arXiv 30 Aug 2025.

Builds on

26 of 39 references.

References · 26

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  7. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  8. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
  9. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 836
  10. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 807
  11. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  12. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
14 more
  1. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  2. 2020Fact or Fiction: Verifying Scientific Claimscited by 554
  3. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 530
  4. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  5. 2019Explain Yourself! Leveraging Language Models for Commonsense Reasoningcited by 367
  6. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  7. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 293
  8. 2019QASC: A Dataset for Question Answering via Sentence Compositioncited by 252
  9. 2021QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarizationcited by 236
  10. 2022Evaluating the Factual Consistency of Large Language Models Through News Summarizationcited by 92
  11. 2019Question Answering for Privacy Policies: Combining Computational and Legal Perspectivescited by 67
  12. 2024Factuality of Large Language Models: A Surveycited by 66
  13. 2024Self-Refine Instruction-Tuning for Aligning Reasoning in Language Modelscited by 24
  14. 2024Are Large Language Models Good at Utility Judgments?cited by 22

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Small Language Models Need Strong Verifiers to Self-Correct Reasoning
  2. 2024A NotSo Simple Way to Beat Simple Bench
  3. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  4. 2023Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
  5. 2025Self-Critique and Refinement for Faithful Natural Language Explanations
  6. 2025Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
  7. 2024TinyThinker: Distilling Reasoning through Coarse-to-Fine Knowledge Internalization with Self-Reflection
  8. 2023REFINER: Reasoning Feedback on Intermediate Representations