English
Related papers

Related papers: There Is More to Refusal in Large Language Models …

200 papers

Novel fundamental notions helping in the interpretation of the complex dynamics of nonlinear systems are essential to our understanding and ability to exploit them. In this work we predict and demonstrate experimentally a fundamental…

Large Language Models (LLMs) rely on safety alignment to obey safe requests while refusing harmful ones. However, traditional refusal mechanisms often lead to "rigid rejection," where a general template (e.g., "I cannot fulfill this…

Computation and Language · Computer Science 2026-05-11 Ying Zhang , Congyu Qiao , Xin Geng , Ning Xu

Multi-modal large language models (MLLMs) have achieved remarkable success on complex multi-modal tasks. However, it remains insufficiently explored whether they exhibit $\textbf{modality preference}$, a tendency to favor one modality over…

Computation and Language · Computer Science 2026-02-05 Yu Zhang , Jinlong Ma , Yongshuai Hou , Xuefeng Bai , Kehai Chen , Yang Xiang , Jun Yu , Min Zhang

Large language models (LLMs) have transformed the way we access information. These models are often tuned to refuse to comply with requests that are considered harmful and to produce responses that better align with the preferences of those…

Computation and Language · Computer Science 2025-08-12 Hannah Cyberey , David Evans

Large language models excel on static benchmarks, but their ability as self-learning agents in dynamic environments remains unclear. We evaluate three prompting strategies: self-reflection, heuristic mutation, and planning across dynamic…

Artificial Intelligence · Computer Science 2025-08-12 Annie Wong , Thomas Bäck , Aske Plaat , Niki van Stein , Anna V. Kononova

Large language models often respond to ambiguous requests by implicitly committing to one interpretation, frustrating users and creating safety risks when that interpretation is wrong. We propose generating a single structured response that…

Computation and Language · Computer Science 2026-04-15 Irina Saparina , Mirella Lapata

Coaxing out desired behavior from pretrained models, while avoiding undesirable ones, has redefined NLP and is reshaping how we interact with computers. What was once a scientific engineering discipline-in which building blocks are stacked…

Machine Learning · Computer Science 2023-08-02 Ari Holtzman , Peter West , Luke Zettlemoyer

Open-weight LLMs can be modified at inference time with simple activation edits, which raises a practical question for safety: do common safety interventions like refusal training or metatag training survive such edits? We study model…

Large language models (LLMs) are increasingly used to generate multiple-choice questions (MCQs), where correct answers should ideally be uniformly distributed across options. However, we observe that LLMs exhibit systematic position biases…

Computation and Language · Computer Science 2026-05-05 Xuemei Tang , Xufeng Duan , Zhenguang G. Cai

Large Language Models (LLMs) like gpt-3.5-turbo-0613 and claude-instant-1.2 are vital in interpreting and executing semantic tasks. Unfortunately, these models' inherent biases adversely affect their performance Particularly affected is…

Computation and Language · Computer Science 2024-06-18 J. E. Eicher , R. F. Irgolič

Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two comprehensive benchmarks: the Exaggerated Safety Benchmark…

Computation and Language · Computer Science 2025-12-19 Shuzhou Yuan , Ercong Nie , Yinuo Sun , Chenxuan Zhao , William LaCroix , Michael Färber

This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which compromises the models' ability to appropriately refuse…

Computation and Language · Computer Science 2025-05-26 Youliang Yuan , Wenxiang Jiao , Wenxuan Wang , Jen-tse Huang , Jiahao Xu , Tian Liang , Pinjia He , Zhaopeng Tu

Current large language models have dangerous capabilities, which are likely to become more problematic in the future. Activation steering techniques can be used to reduce risks from these capabilities. In this paper, we investigate the…

Machine Learning · Computer Science 2024-03-12 Teun van der Weij , Massimo Poesio , Nandi Schoots

In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations at each transformer block. We find that refusal is linearly…

Artificial Intelligence · Computer Science 2026-05-28 Matteo Gioele Collu , Riccardo Conte , Alberto Giaretta , Denis Kleyko , Mauro Conti , Matteo Zavatteri , Roberto Confalonieri

Large Language Models (LLMs) exhibit strong conversational abilities but often generate falsehoods. Prior work suggests that the truthfulness of simple propositions can be represented as a single linear direction in a model's internal…

Machine Learning · Computer Science 2025-05-29 Stanley Yu , Vaidehi Bulusu , Oscar Yasunaga , Clayton Lau , Cole Blondin , Sean O'Brien , Kevin Zhu , Vasu Sharma

Polemic questions need more than one viewpoint to express a balanced answer. Large Language Models (LLMs) can provide a balanced answer, but also take a single aligned viewpoint or refuse to answer. In this paper, we study if such initial…

Computation and Language · Computer Science 2026-02-09 Pedro Cisneros-Velarde

The conformity bias exhibited by large language models (LLMs) can pose a significant challenge to decision-making in LLM-based multi-agent systems (LLM-MAS). While many prior studies have treated "conformity" simply as a matter of opinion…

Artificial Intelligence · Computer Science 2026-04-22 Mikako Bito , Keita Nishimoto , Kimitaka Asatani , Ichiro Sakata

Language models often exhibit undesirable behavior, e.g., generating toxic or gender-biased text. In the case of neural language models, an encoding of the undesirable behavior is often present in the model's representations. Thus, one…

Machine Learning · Computer Science 2025-06-05 Shashwat Singh , Shauli Ravfogel , Jonathan Herzig , Roee Aharoni , Ryan Cotterell , Ponnurangam Kumaraguru

Language models (LMs) are increasingly used to build agents that can act autonomously to achieve goals. During this automatic process, agents need to take a series of actions, some of which might lead to severe consequences if incorrect…

Computation and Language · Computer Science 2025-10-01 Cheng-Kuang Wu , Zhi Rui Tam , Chieh-Yen Lin , Yun-Nung Chen , Hung-yi Lee

Large language models have recently demonstrated remarkable abilities to self-correct their responses through iterative refinement, often referred to as self-consistency or self-reflection. However, the dynamics of this self-correction…

Computation and Language · Computer Science 2025-11-13 Hossein A. Rahmani , Satyapriya Krishna , Xi Wang , Mohammadmehdi Naghiaei , Emine Yilmaz
‹ Prev 1 4 5 6 7 8 10 Next ›