Self-critiquing models for assisting human evaluators

• URL: http://arxiv.org/abs/2206.05802v2
• Date: Tue, 14 Jun 2022 01:16:24 GMT
• Title: Self-critiquing models for assisting human evaluators
• Authors: William Saunders, Catherine Yeh, Jeff Wu, Steven Bills, Long Ouyang, Jonathan Ward, Jan Leike
• Abstract summary: We fine-tune large language models to write natural language critiques (natural language critical comments) using behavioral cloning. On a topic-based summarization task, critiques written by our models help humans find flaws in summaries that they would have otherwise missed. Larger models write more helpful critiques, and on most tasks, are better at self-critiquing, despite having harder-to-critique outputs.
• Score: 11.1006983438712
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We fine-tune large language models to write natural language critiques (natural language critical comments) using behavioral cloning. On a topic-based summarization task, critiques written by our models help humans find flaws in summaries that they would have otherwise missed. Our models help find naturally occurring flaws in both model and human written summaries, and intentional flaws in summaries written by humans to be deliberately misleading. We study scaling properties of critiquing with both topic-based summarization and synthetic tasks. Larger models write more helpful critiques, and on most tasks, are better at self-critiquing, despite having harder-to-critique outputs. Larger models can also integrate their own self-critiques as feedback, refining their own summaries into better ones. Finally, we motivate and introduce a framework for comparing critiquing ability to generation and discrimination ability. Our measurements suggest that even large models may still have relevant knowledge they cannot or do not articulate as critiques. These results are a proof of concept for using AI-assisted human feedback to scale the supervision of machine learning systems to tasks that are difficult for humans to evaluate directly. We release our training datasets, as well as samples from our critique assistance experiments.

Related papers

• Enabling Scalable Oversight via Self-Evolving Critic [59.861013614500024]
  SCRIT (Self-evolving CRITic) is a framework that enables genuine self-evolution of critique abilities. It self-improves by training on synthetic data, generated by a contrastive-based self-critic. It achieves up to a 10.3% improvement on critique-correction and error identification benchmarks.
  arXiv  Detail & Related papers  (2025-01-10T05:51:52Z)
• The Superalignment of Superhuman Intelligence with Large Language Models [63.96120398355404]
  We discuss the concept of superalignment from the learning perspective to answer this question. We highlight some key research problems in superalignment, namely, weak-to-strong generalization, scalable oversight, and evaluation. We present a conceptual framework for superalignment, which consists of three modules: an attacker which generates adversary queries trying to expose the weaknesses of a learner model; a learner which will refine itself by learning from scalable feedbacks generated by a critic model along with minimal human experts; and a critic which generates critics or explanations for a given query-response pair, with a target of improving the learner by criticizing.
  arXiv  Detail & Related papers  (2024-12-15T10:34:06Z)
• Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision [120.40788744292739]
  We propose a two-player paradigm that separates the roles of reasoning and critique models. We first propose AutoMathCritique, an automated and scalable framework for collecting critique data. We demonstrate that the critique models consistently improve the actor's performance on difficult queries at test-time.
  arXiv  Detail & Related papers  (2024-11-25T17:11:54Z)
• CriticAL: Critic Automation with Language Models [31.1575961776287]
  CriticAL generates summary statistics that capture discrepancies between model predictions and data. CriticAL reliably generates correct critiques without hallucinating incorrect ones.
  arXiv  Detail & Related papers  (2024-11-10T20:41:35Z)
• Critique Ability of Large Language Models [38.34144195927209]
  This study explores the ability of large language models (LLMs) to deliver accurate critiques across various tasks. We develop a benchmark called CriticBench, which comprises 3K high-quality natural language queries and corresponding model responses.
  arXiv  Detail & Related papers  (2023-10-07T14:12:15Z)
• UltraFeedback: Boosting Language Models with Scaled AI Feedback [99.4633351133207]
  We present textscUltraFeedback, a large-scale, high-quality, and diversified AI feedback dataset. Our work validates the effectiveness of scaled AI feedback data in constructing strong open-source chat language models.
  arXiv  Detail & Related papers  (2023-10-02T17:40:01Z)
• RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs [27.777809444120827]
  Previous work proposed providing language models with natural language feedback to guide them in repairing their outputs. We introduce RL4F, a multi-agent collaborative framework where critique generator is trained to maximize end-task performance of GPT-3. We show relative improvements up to 10% in multiple text similarity metrics over other learned, retrieval-augmented or prompting-based critique generators.
  arXiv  Detail & Related papers  (2023-05-15T17:57:16Z)
• Training Language Models with Language Feedback at Scale [50.70091340506957]
  We introduce learning from Language Feedback (ILF), a new approach that utilizes more informative language feedback. ILF consists of three steps that are applied iteratively: first, conditioning the language model on the input, an initial LM output, and feedback to generate refinements. We show theoretically that ILF can be viewed as Bayesian Inference, similar to Reinforcement Learning from human feedback.
  arXiv  Detail & Related papers  (2023-03-28T17:04:15Z)
• Chain of Hindsight Aligns Language Models with Feedback [62.68665658130472]
  We propose a novel technique, Chain of Hindsight, that is easy to optimize and can learn from any form of feedback, regardless of its polarity. We convert all types of feedback into sequences of sentences, which are then used to fine-tune the model. By doing so, the model is trained to generate outputs based on feedback, while learning to identify and correct negative attributes or errors.
  arXiv  Detail & Related papers  (2023-02-06T10:28:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.