English
Related papers

Related papers: Confidence Regulation Neurons in Language Models

200 papers

Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM reliability. While prior entropy-based attacks maximize…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Mengqi He , Xinyu Tian , Xin Shen , Jinhong Ni , Shu Zou , Zhaoyuan Yang , Jing Zhang

As large language models (LLMs) advance in their linguistic capacity, understanding how they capture aspects of language competence remains a significant challenge. This study therefore employs psycholinguistic paradigms in English, which…

Computation and Language · Computer Science 2024-12-12 Xufeng Duan , Xinyu Zhou , Bei Xiao , Zhenguang G. Cai

Large Language Models (LLMs) have an unrivaled and invaluable ability to "align" their output to a diverse range of human preferences, by mirroring them in the text they generate. The internal characteristics of such models, however, remain…

Computation and Language · Computer Science 2024-07-08 Brenden Smith , Dallin Baker , Clayton Chase , Myles Barney , Kaden Parker , Makenna Allred , Peter Hu , Alex Evans , Nancy Fulda

As large language models (LLMs) continue to advance, their capacity to function effectively across a diverse range of languages has shown marked improvement. Preliminary studies observe that the hidden activations of LLMs often resemble…

Computation and Language · Computer Science 2025-06-12 Yuxin Chen , Yiran Zhao , Yang Zhang , An Zhang , Kenji Kawaguchi , Shafiq Joty , Junnan Li , Tat-Seng Chua , Michael Qizhe Shieh , Wenxuan Zhang

The emergence of discourse-like tokens such as "wait" and "therefore" in large language models (LLMs) has offered a unique window into their reasoning processes. However, systematic analyses of how such signals vary across training…

Computation and Language · Computer Science 2026-01-27 Jaehui Hwang , Dongyoon Han , Sangdoo Yun , Byeongho Heo

An effective way to scale up test-time compute of large language models is to sample multiple responses and then select the best one, as in Grok Heavy and Gemini Deep Think. Existing selection methods often rely on external reward models,…

Machine Learning · Computer Science 2026-05-04 Wenshuo Zhao , Qi Zhu , Xingshan Zeng , Fei Mi , Lifeng Shang , Yi R. , Fung

Large language models (LLMs) often solve problems using step-by-step Chain-of-Thought (CoT) reasoning, yet these intermediate steps are frequently unfaithful or hard to interpret. Inspired by the Uniform Information Density (UID) hypothesis…

Computation and Language · Computer Science 2025-10-21 Minju Gwak , Guijin Son , Jaehyung Kim

Evaluating whether large language models (LLMs) capture the structure of natural language beyond local fluency remains an open challenge. Existing evaluation methods, largely based on task performance or short-context behavior, provide…

Computation and Language · Computer Science 2026-05-26 Kumiko Tanaka-Ishii

This paper investigates how LLMs encode inputs with typos. We hypothesize that specific neurons and attention heads recognize typos and fix them internally using local and global contexts. We introduce a method to identify typo neurons and…

Computation and Language · Computer Science 2025-02-28 Kohei Tsuji , Tatsuya Hiraoka , Yuchang Cheng , Eiji Aramaki , Tomoya Iwakura

Large Language Models have revolutionized information processing, yet their reliability is severely compromised by faithfulness hallucinations. While current approaches attempt to mitigate this issue through node-level adjustments or coarse…

Computation and Language · Computer Science 2026-01-06 Chenxu Wang , Chaozhuo Li , Pengbo Wang , Litian Zhang , Songyang Liu , Ji Qi , Jiahui Hu , Yushan Cai , Hao Zhao , Rui Pu

Uncertainty quantification in Large Language Models (LLMs) is crucial for applications where safety and reliability are important. In particular, uncertainty can be used to improve the trustworthiness of LLMs by detecting factually…

Machine Learning · Computer Science 2024-05-31 Alexander Nikitin , Jannik Kossen , Yarin Gal , Pekka Marttinen

Predicting upcoming words is a core mechanism of language comprehension and may be quantified using Shannon entropy. There is currently no empirical consensus on how many human responses are required to obtain stable and unbiased entropy…

Computation and Language · Computer Science 2026-02-05 Estrella Pivel-Villanueva , Elisabeth Frederike Sterner , Franziska Knolle

Large Language Models (LLMs) have emerged as dominant foundational models in modern NLP. However, the understanding of their prediction processes and internal mechanisms, such as feed-forward networks (FFN) and multi-head self-attention…

Computation and Language · Computer Science 2024-04-16 Xintong Wang , Xiaoyu Li , Xingshan Li , Chris Biemann

Recent audio-aware large language models (ALLMs) have demonstrated strong capabilities across diverse audio understanding and reasoning tasks, but they still frequently produce hallucinated or overly confident outputs. While uncertainty…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-29 Chun-Yi Kuan , Wei-Ping Huang , Hung-yi Lee

Existing analyses of neural network training often operate under the unrealistic assumption of an extremely small learning rate. This lies in stark contrast to practical wisdom and empirical studies, such as the work of J. Cohen et al.…

Machine Learning · Computer Science 2023-10-20 Kwangjun Ahn , Sébastien Bubeck , Sinho Chewi , Yin Tat Lee , Felipe Suarez , Yi Zhang

Understanding the fundamental principles behind the massive success of neural networks is one of the most important open questions in deep learning. However, due to the highly complex nature of the problem, progress has been relatively…

Machine Learning · Computer Science 2021-12-13 Lechao Xiao

Despite their impressive capabilities, Large Language Models (LLMs) exhibit unwanted uncertainty, a phenomenon where a model changes a previously correct answer into an incorrect one when re-prompted. This behavior undermines trust and…

Computation and Language · Computer Science 2025-10-28 Tiasa Singha Roy , Ayush Rajesh Jhaveri , Ilias Triantafyllopoulos

Neural networks have dramatically increased our capacity to learn from large, high-dimensional datasets across innumerable disciplines. However, their decisions are not easily interpretable, their computational costs are high, and building…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Mackenzie J. Meni , Ryan T. White , Michael Mayo , Kevin Pilkiewicz

Large language models (LLMs) exhibit strong generative capabilities but remain vulnerable to confabulations, fluent yet unreliable outputs that vary arbitrarily even under identical prompts. Leveraging a quantum tensor network based…

Computation and Language · Computer Science 2026-02-03 Pragatheeswaran Vipulanandan , Kamal Premaratne , Dilip Sarkar

While Large Language Models (LLMs) have demonstrated impressive capabilities, their output quality remains inconsistent across various application scenarios, making it difficult to identify trustworthy responses, especially in complex tasks…