mlsanityData to 14 Oct 2026

RankAlign: A Ranking View of the Generator-Validator Gap in Large Language Models

arXiv 2504.11381 ↗First posted 15 Apr 2025cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Although large language models (LLMs) have become more capable and accurate across many tasks, some fundamental sources of unreliability remain in their behavior. One key limitation is their inconsistency at reporting the same information when prompts are changed. In this paper, we consider the discrepancy between a model's generated answer and their own verification of that answer, the generator-validator gap. We define this gap in a more stringent way than prior work: we expect correlation of scores from a generator and a validator over the entire set of candidate answers, i.e., candidate completions that could possibly arise during ordinary language use without breaking Gricean norms. We show that according to this measure, a large gap exists in various settings, including question answering, lexical semantics tasks, and next-word prediction. We then propose RankAlign, a ranking-based training method, and show that it significantly closes the gap, surpassing all baseline methods. Moreover, this approach generalizes well to out-of-domain tasks and lexical items.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 40 of its 63 references that are in the map. First posted on arXiv 15 Apr 2025.

Builds on

40 of 63 references.

References · 40

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  2. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  3. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  4. 2023Large Language Models are not Fair Evaluatorscited by 1,085
  5. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  6. 2016The LAMBADA dataset: Word prediction requiring a broad discourse contextcited by 992
  7. 2019How Can We Know What Language Models Know?cited by 959
  8. 2024Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluatorscited by 897
  9. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  10. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 486
  11. 2023UltraFeedback: Boosting Language Models with Scaled AI Feedbackcited by 406
  12. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 364
28 more
  1. 2023Evaluating the Ripple Effects of Knowledge Editing in Language Modelscited by 242
  2. 2022Measuring Progress on Scalable Oversight for Large Language Modelscited by 225
  3. 2024Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judgecited by 204
  4. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 180
  5. 2024Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithmscited by 143
  6. 2023A Critical Evaluation of Evaluations for Long-form Question Answeringcited by 111
  7. 2023The Generative AI Paradox: "What It Can Create, It May Not Understand"cited by 98
  8. 2023Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineeringcited by 94
  9. 2023On the Calibration of Large Language Models and Alignmentcited by 73
  10. 2023Split and Merge: Aligning Position Biases in LLM-based Evaluatorscited by 72
  11. 2024"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Modelscited by 69
  12. 2024Are Large Language Models Consistent over Value-laden Questions?cited by 58
  13. 2024LoFiT: Localized Fine-tuning on LLM Representationscited by 57
  14. 2023SALMON: Self-Alignment with Instructable Reward Modelscited by 55
  15. 2024Auxiliary task demands mask the capabilities of smaller language modelscited by 54
  16. 2023Benchmarking and Improving Generator-Validator Consistency of Language Modelscited by 44
  17. 2023Unveiling the Pitfalls of Knowledge Editing for Large Language Modelscited by 43
  18. 2024CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judgescited by 34
  19. 2025Language Models Fail to Introspect About Their Knowledge of Languagecited by 30
  20. 2024Learning to Refine with Fine-Grained Natural Language Feedbackcited by 27
  21. 2024SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responsescited by 26
  22. 2024Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?cited by 24
  23. 2024Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Thinkcited by 14
  24. 2021Swords: A Benchmark for Lexical Substitution with Improved Data Coverage and Qualitycited by 13
  25. 2023Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Modelscited by 11
  26. 2024Characterizing the Role of Similarity in the Property Inferences of Language Modelscited by 11
  27. 2024Are language models rational? The case of coherence norms and belief revisioncited by 10
  28. 2024Defining Knowledge: Bridging Epistemology and Large Language Modelscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Calibrating Verbalized Confidence with Self-Generated Distractorscited by 14
  2. 2026Aletheia: What Makes RLVR For Code Verifiers Tick?cited by 5
  3. 2025On Evaluating LLM Alignment by Evaluating LLMs as Judgescited by 3
  4. 2026Distilling Directional Verificationcited by 0