paper-with-me

홈 › Papers

Calibrating the Confidence of Large Language Models by Eliciting Fidelity

2024-04-03 · Mozhi Zhang, Mianqiu Huang, Rundong Shi, Linsen Guo, Chong Peng, Peng Yan, Yaqian Zhou, Xipeng Qiu

Large language models optimized with techniques like RLHF have achieved good alignment in being helpful and harmless. However, post-alignment, these language models often exhibit overconfidence, where the expressed confidence does not accurately calibrate with their correctness rate. In this paper, we decompose the language model confidence into the \textit{Uncertainty} about the question and the \textit{Fidelity} to the answer generated by language models. Then, we propose a plug-and-play method to estimate the confidence of language models. Our method has shown good calibration performance by conducting experiments with 6 RLHF-LMs on four MCQA datasets. Moreover, we propose two novel metrics, IPR and CE, to evaluate the calibration of the model, and we have conducted a detailed discussion on \textit{Truly Well-Calibrated Confidence}. Our method could serve as a strong baseline, and we hope that this work will provide some insights into the model confidence calibration.

📄 PDF Abstract BibTeX arXiv:2404.02655

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Enhancing Healthcare LLM Trust with Atypical Presentations Recalibration

2024-09-05 · Jeremy Qin, Bang Liu, Quoc Dinh Nguyen

Black-box large language models (LLMs) are increasingly deployed in various environments, making it essential for these models to effectively convey their confidence and uncertainty, especially in high-stakes settings. H…

Decision MakingMedical Question AnsweringQuestion Answering

Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies

2025-05-27 · Terrance Liu, Shuyi Wang, Daniel Preotiuc-Pietro, Yash Chandarana 외

While large language models (LLMs) achieve strong performance on text-to-SQL parsing, they sometimes exhibit unexpected failures in which they are confidently incorrect. Building trustworthy text-to-SQL systems thus requ…

SQL ParsingText to SQLText-To-SQL

I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation

2026-04-05 · Haotian Zong, Binze Li, Yufei Long, Sinyin Chang 외 arxiv

Large language models (LLMs) frequently produce confident but incorrect answers, partly because common binary scoring conventions reward answering over honestly expressing uncertainty. We study whether prompt-only interv…

Calibrating Multimodal Learning

2023-06-02 · Huan Ma. Qingyang Zhang, Changqing Zhang, Bingzhe Wu, Huazhu Fu 외

Multimodal machine learning has achieved remarkable progress in a wide range of scenarios. However, the reliability of multimodal learning remains largely unexplored. In this paper, through extensive empirical studies, w…

Calibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding

2025-04-30 · Trilok Padhi, Ramneet Kaur, Adam D. Cobb, Manoj Acharya 외

We introduce a novel approach for calibrating uncertainty quantification (UQ) tailored for multi-modal large language models (LLMs). Existing state-of-the-art UQ methods rely on consistency among multiple responses gener…

Medical Question AnsweringQuestion AnsweringUncertainty QuantificationVisual Question Answering