ConfQA: Answer Only If You Are Confident

• URL: http://arxiv.org/abs/2506.07309v1
• Date: Sun, 08 Jun 2025 22:51:46 GMT
• Title: ConfQA: Answer Only If You Are Confident
• Authors: Yin Huang, Yifan Ethan Xu, Kai Sun, Vera Yan, Alicia Sun, Haidar Khan, Jimmy Nguyen, Mohammad Kachuee, Zhaojiang Lin, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong,
• Abstract summary: We present a fine-tuning strategy that we call ConfQA, which can reduce hallucination rate from 20-40% to under 5% across multiple factuality benchmarks.<n>We introduce a dampening prompt "answer only if you are confident" to explicitly guide the behavior, without which hallucination remains high as 15%-25%.<n>We propose the Dual Neural Knowledge framework, which seamlessly select between internally parameterized neural knowledge and externally recorded symbolic knowledge.
• Score: 49.34040922485979
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Can we teach Large Language Models (LLMs) to refrain from hallucinating factual statements? In this paper we present a fine-tuning strategy that we call ConfQA, which can reduce hallucination rate from 20-40% to under 5% across multiple factuality benchmarks. The core idea is simple: when the LLM answers a question correctly, it is trained to continue with the answer; otherwise, it is trained to admit "I am unsure". But there are two key factors that make the training highly effective. First, we introduce a dampening prompt "answer only if you are confident" to explicitly guide the behavior, without which hallucination remains high as 15%-25%. Second, we leverage simple factual statements, specifically attribute values from knowledge graphs, to help LLMs calibrate the confidence, resulting in robust generalization across domains and question types. Building on this insight, we propose the Dual Neural Knowledge framework, which seamlessly select between internally parameterized neural knowledge and externally recorded symbolic knowledge based on ConfQA's confidence. The framework enables potential accuracy gains to beyond 95%, while reducing unnecessary external retrievals by over 30%.

Related papers

• When Two LLMs Debate, Both Think They'll Win [0.0]
  We evaluate Large Language Models (LLMs) in a dynamic, adversarial debate setting.<n>We organized 60 three-round policy debates among ten state-of-the-art LLMs.<n>We observed five concerning patterns.
  arXiv  Detail & Related papers  (2025-05-25T15:06:17Z)
• Inside-Out: Hidden Factual Knowledge in LLMs [50.79758420289131]
  This work presents a framework for assessing whether large language models (LLMs) encode more factual knowledge in their parameters than what they express in their outputs.<n>We first propose a formal definition of knowledge, quantifying it for a given question as the fraction of correct-incorrect answer pairs where the correct one is ranked higher.<n>We then present a case study, applying this framework to three popular open-weights LLMs in a closed-book QA setup.
  arXiv  Detail & Related papers  (2025-03-19T15:21:48Z)
• Learning to Route LLMs with Confidence Tokens [43.63392143501436]
  We study the extent to which large language models can reliably indicate confidence in their answers.<n>We propose Self-REF, a lightweight training strategy to teach LLMs to express confidence in a reliable manner.<n>Compared to conventional approaches such as verbalizing confidence and examining token probabilities, we demonstrate empirically that confidence tokens show significant improvements in downstream routing and rejection learning tasks.
  arXiv  Detail & Related papers  (2024-10-17T07:28:18Z)
• Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence? [26.69630281310365]
  Large language models (LLMs) have been found to produce hallucinations when the question exceeds their internal knowledge boundaries. Existing research on LLMs' perception of their knowledge boundaries typically uses either the probability of the generated tokens or the verbalized confidence as the model's confidence in its response.
  arXiv  Detail & Related papers  (2024-08-19T08:01:11Z)
• LLM Internal States Reveal Hallucination Risk Faced With a Query [62.29558761326031]
  Humans have a self-awareness process that allows us to recognize what we don't know when faced with queries. This paper investigates whether Large Language Models can estimate their own hallucination risk before response generation. By a probing estimator, we leverage LLM self-assessment, achieving an average hallucination estimation accuracy of 84.32% at run time.
  arXiv  Detail & Related papers  (2024-07-03T17:08:52Z)
• LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models [69.68379406317682]
  We introduce a listener-aware finetuning method (LACIE) to calibrate implicit and explicit confidence markers. We show that LACIE models the listener, considering not only whether an answer is right, but whether it will be accepted by a listener. We find that training with LACIE results in 47% fewer incorrect answers being accepted while maintaining the same level of acceptance for correct answers.
  arXiv  Detail & Related papers  (2024-05-31T17:16:38Z)
• Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation [9.730412606588335]
  We evaluate the ability of Large Language Models (LLMs) to discern and express their internal knowledge state. We propose a Reinforcement Learning from Knowledge Feedback (RLKF) training framework, leveraging reinforcement learning to enhance the factuality and honesty of LLMs.
  arXiv  Detail & Related papers  (2024-01-27T16:19:30Z)
• Knowledge Verification to Nip Hallucination in the Bud [69.79051730580014]
  We demonstrate the feasibility of mitigating hallucinations by verifying and minimizing the inconsistency between external knowledge present in the alignment data and the intrinsic knowledge embedded within foundation LLMs. We propose a novel approach called Knowledge Consistent Alignment (KCA), which employs a well-aligned LLM to automatically formulate assessments based on external knowledge. We demonstrate the superior efficacy of KCA in reducing hallucinations across six benchmarks, utilizing foundation LLMs of varying backbones and scales.
  arXiv  Detail & Related papers  (2024-01-19T15:39:49Z)
• Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs [60.61002524947733]
  Previous confidence elicitation methods rely on white-box access to internal model information or model fine-tuning. This leads to a growing need to explore the untapped area of black-box approaches for uncertainty estimation. We define a systematic framework with three components: prompting strategies for eliciting verbalized confidence, sampling methods for generating multiple responses, and aggregation techniques for computing consistency.
  arXiv  Detail & Related papers  (2023-06-22T17:31:44Z)
• How Much Can We Really Trust You? Towards Simple, Interpretable Trust Quantification Metrics for Deep Neural Networks [94.65749466106664]
  We conduct a thought experiment and explore two key questions about trust in relation to confidence. We introduce a suite of metrics for assessing the overall trustworthiness of deep neural networks based on their behaviour when answering a set of questions. The proposed metrics are by no means perfect, but the hope is to push the conversation towards better metrics.
  arXiv  Detail & Related papers  (2020-09-12T17:37:36Z)

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.