Alignment for Honesty

• URL: http://arxiv.org/abs/2312.07000v2
• Date: Mon, 28 Oct 2024 05:15:30 GMT
• Title: Alignment for Honesty
• Authors: Yuqing Yang, Ethan Chern, Xipeng Qiu, Graham Neubig, Pengfei Liu,
• Abstract summary: Recent research has made significant strides in aligning large language models (LLMs) with helpfulness and harmlessness. In this paper, we argue for the importance of alignment for emphhonesty, ensuring that LLMs proactively refuse to answer questions when they lack knowledge. We address these challenges by first establishing a precise problem definition and defining honesty'' inspired by the Analects of Confucius.
• Score: 105.72465407518325
• License:
• Abstract: Recent research has made significant strides in aligning large language models (LLMs) with helpfulness and harmlessness. In this paper, we argue for the importance of alignment for \emph{honesty}, ensuring that LLMs proactively refuse to answer questions when they lack knowledge, while still not being overly conservative. However, a pivotal aspect of alignment for honesty involves discerning an LLM's knowledge boundaries, which demands comprehensive solutions in terms of metric development, benchmark creation, and training methodologies. We address these challenges by first establishing a precise problem definition and defining ``honesty'' inspired by the Analects of Confucius. This serves as a cornerstone for developing metrics that effectively measure an LLM's honesty by quantifying its progress post-alignment. Furthermore, we introduce a flexible training framework which is further instantiated by several efficient fine-tuning techniques that emphasize honesty without sacrificing performance on other tasks. Our extensive experiments reveal that these aligned models show a marked increase in honesty, as indicated by our proposed metrics. We open-source all relevant resources to facilitate future research at \url{https://github.com/GAIR-NLP/alignment-for-honesty}.

Related papers

• FactAlign: Long-form Factuality Alignment of Large Language Models [35.067998820937284]
  Large language models have demonstrated significant potential as the next-generation information access engines. We propose FactAlign, a novel alignment framework designed to enhance the factuality of long-form responses. Our experiments on open-domain prompts and information-seeking questions demonstrate that FactAlign significantly improves the factual accuracy of LLM responses.
  arXiv  Detail & Related papers  (2024-10-02T16:03:13Z)
• A Survey on the Honesty of Large Language Models [115.8458596738659]
  Honesty is a fundamental principle for aligning large language models (LLMs) with human values. Despite promising, current LLMs still exhibit significant dishonest behaviors.
  arXiv  Detail & Related papers  (2024-09-27T14:34:54Z)
• BeHonest: Benchmarking Honesty in Large Language Models [23.192389530727713]
  We introduce BeHonest, a pioneering benchmark specifically designed to assess honesty in Large Language Models. BeHonest evaluates three essential aspects of honesty: awareness of knowledge boundaries, avoidance of deceit, and consistency in responses. Our findings indicate that there is still significant room for improvement in the honesty of LLMs.
  arXiv  Detail & Related papers  (2024-06-19T06:46:59Z)
• CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models [60.59638232596912]
  We introduce CLAMBER, a benchmark for evaluating large language models (LLMs) Building upon the taxonomy, we construct 12K high-quality data to assess the strengths, weaknesses, and potential risks of various off-the-shelf LLMs. Our findings indicate the limited practical utility of current LLMs in identifying and clarifying ambiguous user queries.
  arXiv  Detail & Related papers  (2024-05-20T14:34:01Z)
• Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness [39.74642729786543]
  We argue that current factuality enhancement methods can significantly undermine context-faithfulness of large language models (LLMs) Experiments reveal that while these methods may yield inconsistent improvements in factual accuracy, they also cause a more severe decline in context-faithfulness.
  arXiv  Detail & Related papers  (2024-03-30T02:08:28Z)
• SaGE: Evaluating Moral Consistency in Large Language Models [15.079905222871071]
  We show that even state-of-the-art Large Language Models are morally inconsistent in their generations. We propose an information-theoretic measure called Semantic Graph Entropy (SaGE) to measure a model's moral consistency.
  arXiv  Detail & Related papers  (2024-02-21T11:23:21Z)
• Best Practices for Text Annotation with Large Language Models [11.421942894219901]
  Large Language Models (LLMs) have ushered in a new era of text annotation. This paper proposes a comprehensive set of standards and best practices for their reliable, reproducible, and ethical use.
  arXiv  Detail & Related papers  (2024-02-05T15:43:50Z)
• Fake Alignment: Are LLMs Really Aligned Well? [91.26543768665778]
  This study investigates the substantial discrepancy in performance between multiple-choice questions and open-ended questions. Inspired by research on jailbreak attack patterns, we argue this is caused by mismatched generalization.
  arXiv  Detail & Related papers  (2023-11-10T08:01:23Z)
• Towards Verifiable Generation: A Benchmark for Knowledge-aware Language Model Attribution [48.86322922826514]
  This paper defines a new task of Knowledge-aware Language Model Attribution (KaLMA) First, we extend attribution source from unstructured texts to Knowledge Graph (KG), whose rich structures benefit both the attribution performance and working scenarios. Second, we propose a new Conscious Incompetence" setting considering the incomplete knowledge repository. Third, we propose a comprehensive automatic evaluation metric encompassing text quality, citation quality, and text citation alignment.
  arXiv  Detail & Related papers  (2023-10-09T11:45:59Z)
• Context-faithful Prompting for Large Language Models [51.194410884263135]
  Large language models (LLMs) encode parametric knowledge about world facts. Their reliance on parametric knowledge may cause them to overlook contextual cues, leading to incorrect predictions in context-sensitive NLP tasks. We assess and enhance LLMs' contextual faithfulness in two aspects: knowledge conflict and prediction with abstention.
  arXiv  Detail & Related papers  (2023-03-20T17:54:58Z)

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.