中文
相关论文

相关论文: Reconfidencing LLMs from the Grouping Loss Perspec…

200 篇论文

Large language models (LLMs) have revolutionized the field of natural language processing with their impressive reasoning and question-answering capabilities. However, these models are sometimes prone to generating credible-sounding but…

计算与语言 · 计算机科学 2026-04-21 Ranganath Krishnan , Piyush Khanna , Omesh Tickoo

A trustworthy real-world prediction system should produce well-calibrated confidence scores; that is, its confidence in an answer should be indicative of the likelihood that the answer is correct, enabling deferral to an expert in cases of…

Large Language Models (LLMs) show remarkable proficiency in natural language tasks, yet their frequent overconfidence-misalignment between predicted confidence and true correctness-poses significant risks in critical decision-making…

计算与语言 · 计算机科学 2025-12-15 Prateek Chhikara

To enhance Large Language Models' (LLMs) reliability, calibration is essential -- the model's assessed confidence scores should align with the actual likelihood of its responses being correct. However, current confidence elicitation methods…

计算与语言 · 计算机科学 2024-10-29 Yukun Huang , Yixin Liu , Raghuveer Thirukovalluru , Arman Cohan , Bhuwan Dhingra

As artificial intelligence (AI) systems, particularly large language models (LLMs), become increasingly integrated into decision-making processes, the ability to trust their outputs is crucial. To earn human trust, LLMs must be well…

Large language models (LLMs) are increasingly used in high-stakes settings, where overconfident responses can mislead users. Reliable confidence estimation has been shown to enhance trust and task accuracy. Yet existing methods face…

计算与语言 · 计算机科学 2025-09-30 Linwei Tao , Yi-Fan Yeh , Bo Kai , Minjing Dong , Tao Huang , Tom A. Lamb , Jialin Yu , Philip H. S. Torr , Chang Xu

This paper proposes the use of "multicalibration" to yield interpretable and reliable confidence scores for outputs generated by large language models (LLMs). Multicalibration asks for calibration not just marginally, but simultaneously…

机器学习 · 统计学 2024-04-09 Gianluca Detommaso , Martin Bertran , Riccardo Fogliato , Aaron Roth

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks in various domains. Despite their impressive performance, they can be unreliable due to factual errors in their generations. Assessing their…

计算与语言 · 计算机科学 2024-03-26 Jiahui Geng , Fengyu Cai , Yuxia Wang , Heinz Koeppl , Preslav Nakov , Iryna Gurevych

Large language models (LLMs) are increasingly employed in information-seeking and decision-making tasks. Despite their broad utility, LLMs tend to generate information that conflicts with real-world facts, and their persuasive style can…

计算与语言 · 计算机科学 2024-09-19 Arslan Chaudhry , Sridhar Thiagarajan , Dilan Gorur

There is a growing literature on reasoning by large language models (LLMs), but the discussion on the uncertainty in their responses is still lacking. Our aim is to assess the extent of confidence that LLMs have in their answers and how it…

计算与语言 · 计算机科学 2024-12-23 Yudi Pawitan , Chris Holmes

Large Language Models (LLMs) have been found to have difficulty knowing they do not possess certain knowledge and tend to provide specious answers in such cases. Retrieval Augmentation (RA) has been extensively studied to mitigate LLMs'…

计算与语言 · 计算机科学 2024-06-12 Shiyu Ni , Keping Bi , Jiafeng Guo , Xueqi Cheng

Uncertainty estimation is a significant issue for current large language models (LLMs) that are generally poorly calibrated and over-confident, especially with reinforcement learning from human feedback (RLHF). Unlike humans, whose…

计算与语言 · 计算机科学 2024-05-13 Ruixin Yang , Dheeraj Rajagopal , Shirley Anugrah Hayati , Bin Hu , Dongyeop Kang

We investigate the calibration of large language models' (LLMs') confidence across diverse tasks. The results of our preregistered study show that the current crop of LLMs are, like people, too sure they are right: confidence exceeds…

人工智能 · 计算机科学 2026-05-26 Noam Michael , Daniel BenShushan , Jacob Bien , Don A. Moore

Empowering large language models to accurately express confidence in their answers is essential for trustworthy decision-making. Previous confidence elicitation methods, which primarily rely on white-box access to internal model information…

计算与语言 · 计算机科学 2024-03-19 Miao Xiong , Zhiyuan Hu , Xinyang Lu , Yifei Li , Jie Fu , Junxian He , Bryan Hooi

Large language models (LLMs) are increasingly used in decision-making contexts, but when they present answers without signaling low confidence, users may unknowingly act on erroneous outputs. Prior work shows that LLMs maintain internal…

计算与语言 · 计算机科学 2025-10-23 Mark Steyvers , Catarina Belem , Padhraic Smyth

Large language models (LLMs) exhibit strikingly conflicting behaviors: they can appear steadfastly overconfident in their initial answers whilst at the same time being prone to excessive doubt when challenged. To investigate this apparent…

Large Language Models (LLMs) show promise for automated grading, but their outputs can be unreliable. Rather than improving grading accuracy directly, we address a complementary problem: \textit{predicting when an LLM grader is likely to be…

计算与语言 · 计算机科学 2026-04-01 Robinson Ferrer , Damla Turgut , Zhongzhou Chen , Shashank Sonkar

While large language models (LLMs) improve performance by explicit reasoning, their responses are often overconfident, even though they include linguistic expressions demonstrating uncertainty. In this work, we identify what linguistic…

计算与语言 · 计算机科学 2026-04-08 Shintaro Ozaki , Wataru Hashimoto , Hidetaka Kamigaito , Katsuhiko Hayashi , Taro Watanabe

Large Language Models (LLMs) have acquired ubiquitous attention for their performances across diverse domains. Our study here searches through LLMs' cognitive abilities and confidence dynamics. We dive deep into understanding the alignment…

计算与语言 · 计算机科学 2023-09-29 Aniket Kumar Singh , Suman Devkota , Bishal Lamichhane , Uttam Dhakal , Chandra Dhakal

A safe and trustworthy use of Large Language Models (LLMs) requires an accurate expression of confidence in their answers. We propose a novel Reinforcement Learning approach that allows to directly fine-tune LLMs to express calibrated…

‹ 上一页 1 2 3 10 下一页 ›