Reinforcement Learning for Better Verbalized Confidence in Long-Form Generation

• URL: http://arxiv.org/abs/2505.23912v1
• Date: Thu, 29 May 2025 18:05:20 GMT
• Title: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generation
• Authors: Caiqi Zhang, Xiaochen Zhu, Chengzu Li, Nigel Collier, Andreas Vlachos,
• Abstract summary: We propose LoVeC (Long-form Verbalized Confidence), an on-the-fly verbalized confidence estimation method for long-form generation.<n>Specifically, we use reinforcement learning (RL) to train LLMs to append numerical confidence scores to each generated statement.<n>Our experiments show that our RL-trained models achieve better calibration and generalize robustly across domains.
• Score: 27.811765400370838
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hallucination remains a major challenge for the safe and trustworthy deployment of large language models (LLMs) in factual content generation. Prior work has explored confidence estimation as an effective approach to hallucination detection, but often relies on post-hoc self-consistency methods that require computationally expensive sampling. Verbalized confidence offers a more efficient alternative, but existing approaches are largely limited to short-form question answering (QA) tasks and do not generalize well to open-ended generation. In this paper, we propose LoVeC (Long-form Verbalized Confidence), an on-the-fly verbalized confidence estimation method for long-form generation. Specifically, we use reinforcement learning (RL) to train LLMs to append numerical confidence scores to each generated statement, serving as a direct and interpretable signal of the factuality of generation. Our experiments consider both on-policy and off-policy RL methods, including DPO, ORPO, and GRPO, to enhance the model calibration. We introduce two novel evaluation settings, free-form tagging and iterative tagging, to assess different verbalized confidence estimation methods. Experiments on three long-form QA datasets show that our RL-trained models achieve better calibration and generalize robustly across domains. Also, our method is highly efficient, as it only requires adding a few tokens to the output being decoded.

Related papers

• Post-Training Large Language Models via Reinforcement Learning from Self-Feedback [3.73824942136665]
  Large Language Models (LLMs) often produce plausible but poorly-calibrated answers.<n>We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the model's own confidence as an intrinsic reward.
  arXiv  Detail & Related papers  (2025-07-29T15:46:26Z)
• The Power of Certainty: How Confident Models Lead to Better Segmentation [0.0]
  We propose a confidence-based self-distillation approach that outperforms state-of-the-art models by utilizing only previous data storage during training.<n>Our approach generalizes well across datasets collected from multiple clinical centers.
  arXiv  Detail & Related papers  (2025-07-14T17:12:43Z)
• Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models [34.59785123314865]
  A safe and trustworthy use of Large Language Models (LLMs) requires an accurate expression of confidence in their answers.<n>We propose a novel Reinforcement Learning approach that allows to directly fine-tune LLMs to express calibrated confidence estimates alongside their answers to factual questions.
  arXiv  Detail & Related papers  (2025-03-04T13:48:50Z)
• Scalable Best-of-N Selection for Large Language Models via Self-Certainty [65.31658824274894]
  Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models.<n>We propose self-certainty, a novel and efficient metric to estimate response quality without requiring external reward models.<n>Our findings establish self-certainty as a practical and efficient way for improving LLM reasoning capabilities.
  arXiv  Detail & Related papers  (2025-02-25T19:08:07Z)
• Scaling Test-Time Compute Without Verification or RL is Suboptimal [70.28430200655919]
  We show that finetuning LLMs with verifier-based (VB) methods based on RL or search is far superior to verifier-free (VF) approaches based on distilling or cloning search traces, given a fixed amount of compute/data budget.<n>We corroborate our theory empirically on both didactic and math reasoning problems with 3/8B-sized pre-trained LLMs, where we find verification is crucial for scaling test-time compute.
  arXiv  Detail & Related papers  (2025-02-17T18:43:24Z)
• Self-Improvement in Language Models: The Sharpening Mechanism [70.9248553790022]
  We offer a new perspective on the capabilities of self-improvement through a lens we refer to as sharpening.<n>Motivated by the observation that language models are often better at verifying response quality than they are at generating correct responses, we formalize self-improvement as using the model itself as a verifier during post-training.<n>We analyze two natural families of self-improvement algorithms based on SFT and RLHF.
  arXiv  Detail & Related papers  (2024-12-02T20:24:17Z)
• Graph-based Confidence Calibration for Large Language Models [22.394717844099684]
  We propose using an auxiliary learning model to assess response correctness based on the self-consistency of multiple outputs generated by the large language models.<n>Our method builds a consistency graph to represent the agreement among multiple responses and uses a graph neural network (GNN) to estimate the likelihood that each response is correct.
  arXiv  Detail & Related papers  (2024-11-03T20:36:44Z)
• Calibrating the Confidence of Large Language Models by Eliciting Fidelity [52.47397325111864]
  Large language models optimized with techniques like RLHF have achieved good alignment in being helpful and harmless. Post-alignment, these language models often exhibit overconfidence, where the expressed confidence does not accurately calibrate with their correctness rate. We propose a plug-and-play method to estimate the confidence of language models.
  arXiv  Detail & Related papers  (2024-04-03T11:36:12Z)
• Calibrating Large Language Models Using Their Generations Only [44.26441565763495]
  APRICOT is a method to set confidence targets and train an additional model that predicts an LLM's confidence based on its textual input and output alone. It is conceptually simple, does not require access to the target model beyond its output, does not interfere with the language generation, and has a multitude of potential usages. We show how our approach performs competitively in terms of calibration error for white-box and black-box LLMs on closed-book question-answering to detect incorrect LLM answers.
  arXiv  Detail & Related papers  (2024-03-09T17:46:24Z)
• Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback [91.22679548111127]
  A trustworthy real-world prediction system should produce well-calibrated confidence scores. We show that verbalized confidences emitted as output tokens are typically better-calibrated than the model's conditional probabilities.
  arXiv  Detail & Related papers  (2023-05-24T10:12:33Z)
• Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-To-End Automatic Speech Recognition [86.21889574126878]
  We show how per-frame entropy values can be normalized and aggregated to obtain a confidence measure per unit and per word. We evaluate the proposed confidence measures on LibriSpeech test sets, and show that they are up to 2 and 4 times better than confidence estimation based on the maximum per-frame probability.
  arXiv  Detail & Related papers  (2022-12-16T20:27:40Z)
• Text Generation with Efficient (Soft) Q-Learning [91.47743595382758]
  Reinforcement learning (RL) offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. We introduce a new RL formulation for text generation from the soft Q-learning perspective. We apply the approach to a wide range of tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation.
  arXiv  Detail & Related papers  (2021-06-14T18:48:40Z)

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.