English
Related papers

Related papers: Mitigating Over-Refusal in Aligned Large Language …

200 papers

Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…

Computation and Language · Computer Science 2026-04-21 Yuheng Chen , Zhiyu Wu , Bowen Cheng , Tetsuro Takahashi

Large language models (LLMs) often produce confident but incorrect answers in settings where abstention would be safer. Standard evaluation protocols, however, require a response and do not account for how confidence should guide decisions…

Computation and Language · Computer Science 2026-04-06 Sean Wu , Fredrik K. Gustafsson , Edward Phillips , Boyan Gao , Anshul Thakur , David A. Clifton

Accurate prediction helps to achieve supply-demand balance in energy systems, supporting decision-making and scheduling. Traditional models, lacking AI-assisted automation, rely on experts, incur high costs, and struggle with sparse data…

Machine Learning · Computer Science 2024-12-25 Zihang Qiu , Chaojie Li , Zhongyang Wang , Renyou Xie , Borui Zhang , Huadong Mo , Guo Chen , Zhaoyang Dong

Recent advancements in large language models (LLMs) have demonstrated that fine-tuning and human alignment can render LLMs harmless. In practice, such "harmlessness" behavior is mainly achieved by training models to reject harmful requests,…

Computation and Language · Computer Science 2025-03-25 Shengyun Si , Xinpeng Wang , Guangyao Zhai , Nassir Navab , Barbara Plank

Open-weight large language model (LLM) zoos allow users to quickly integrate state-of-the-art models into systems. Despite increasing availability, selecting the most appropriate model for a given task still largely relies on public…

Machine Learning · Computer Science 2024-11-05 Ryan Zhang , Herbert Woisetschläger , Shiqiang Wang , Hans Arno Jacobsen

Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…

Machine Learning · Computer Science 2025-05-01 Yi Zhou , Wenpeng Xing , Dezhang Kong , Changting Lin , Meng Han

Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs) by enabling audio-based human interactions. However, recent research has revealed that LALMs remain vulnerable to harmful queries due to…

Computation and Language · Computer Science 2025-05-27 Hao Yang , Lizhen Qu , Ehsan Shareghi , Gholamreza Haffari

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…

Cryptography and Security · Computer Science 2026-02-06 Chen Xiong , Zhiyuan He , Pin-Yu Chen , Ching-Yun Ko , Tsung-Yi Ho

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…

Machine Learning · Computer Science 2026-03-09 Kartik Sharma , Rakshit S. Trivedi

While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak attacks that circumvent safety constraints. Existing strategies, ranging from heuristic prompt engineering to computationally…

Artificial Intelligence · Computer Science 2026-04-10 Wenpeng Xing , Moran Fang , Guangtai Wang , Changting Lin , Meng Han

The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in…

Computation and Language · Computer Science 2025-10-17 Riccardo Cantini , Alessio Orsino , Massimo Ruggiero , Domenico Talia

Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust…

Cryptography and Security · Computer Science 2025-11-11 Haonan Shi , Guoli Wang , Tu Ouyang , An Wang

Large language models (LLMs) have achieved remarkable performance across many generation tasks. Nevertheless, effectively aligning them with desired behaviors remains a significant challenge. Activation steering is an effective and…

Computation and Language · Computer Science 2025-10-02 Zifeng Cheng , Jinwei Gan , Zhiwei Jiang , Cong Wang , Yafeng Yin , Xiang Luo , Yuchen Fu , Qing Gu

Finetuning large language models on narrowly harmful datasets can cause them to become emergently misaligned, giving stereotypically `evil' responses across diverse unrelated settings. Concerningly, a pre-registered survey of experts failed…

Artificial Intelligence · Computer Science 2026-02-10 Anna Soligo , Edward Turner , Senthooran Rajamanoharan , Neel Nanda

Large Vision-Language Models (LVLMs) have achieved remarkable success across cross-modal tasks but remain hindered by hallucinations, producing textual outputs inconsistent with visual content. Existing methods mitigate hallucinations but…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Yuanhong Zhang , Zhaoyang Wang , Xin Zhang , Weizhan Zhang , Joey Tianyi Zhou

Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through additional training, we explore an alternative: steering model…

In many statistical learning problems, the target functions to be optimized are highly non-convex in various model spaces and thus are difficult to analyze. In this paper, we compute \emph{Energy Landscape Maps} (ELMs) which characterize…

Machine Learning · Statistics 2014-10-03 Maria Pavlovskaia , Kewei Tu , Song-Chun Zhu

Conventional mechanical design follows an iterative process in which initial concepts are refined through cycles of expert assessment and resource-intensive Finite Element Method (FEM) analysis to meet performance goals. While machine…

Machine Learning · Computer Science 2025-05-02 Yayati Jadhav , Amir Barati Farimani

Large language models (LLMs) exhibit impressive capabilities in generation tasks but are prone to producing harmful, misleading, or biased content, posing significant ethical and safety concerns. To mitigate such risks, representation…

Cryptography and Security · Computer Science 2025-11-17 Zeqing He , Zhibo Wang , Huiyu Xu , Hejun Lin , Wenhui Zhang , Zhixuan Chu

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging, especially in open-ended generation settings. This paper…

Computation and Language · Computer Science 2025-12-08 Zirui He , Mingyu Jin , Bo Shen , Ali Payani , Yongfeng Zhang , Mengnan Du