English
Related papers

Related papers: Characterizing Selective Refusal Bias in Large Lan…

200 papers

Large language models (LLMs) have convincing performance in a variety of downstream tasks. However, these systems are prone to generating undesirable outputs such as harmful and biased text. In order to remedy such generations, the…

Computation and Language · Computer Science 2025-08-08 Manish Nagireddy , Inkit Padhi , Soumya Ghosh , Prasanna Sattigeri

Current LLMs are trained to refuse potentially harmful input queries regardless of whether users actually had harmful intents, causing a tradeoff between safety and user experience. Through a study of 480 participants evaluating 3,840…

Computation and Language · Computer Science 2025-12-04 Mingqian Zheng , Wenjia Hu , Patrick Zhao , Motahhare Eslami , Jena D. Hwang , Faeze Brahman , Carolyn Rose , Maarten Sap

The potential effectiveness of counterspeech as a hate speech mitigation strategy is attracting increasing interest in the NLG research community, particularly towards the task of automatically producing it. However, automatically generated…

Computation and Language · Computer Science 2024-10-07 Helena Bonaldi , Greta Damo , Nicolás Benjamín Ocampo , Elena Cabrio , Serena Villata , Marco Guerini

As modern Large Language Models (LLMs) shatter many state-of-the-art benchmarks in a variety of domains, this paper investigates their behavior in the domains of ethics and fairness, focusing on protected group bias. We conduct a two-part…

Computers and Society · Computer Science 2024-03-25 Hadas Kotek , David Q. Sun , Zidi Xiu , Margit Bowler , Christopher Klein

Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased…

Computation and Language · Computer Science 2024-09-05 Zhixuan Chu , Yan Wang , Longfei Li , Zhibo Wang , Zhan Qin , Kui Ren

Large Language Models (LLMs) are trained to refuse to respond to harmful content. However, systematic analyses of whether this behavior is truly a reflection of its safety policies or an indication of political censorship, that is practiced…

Computation and Language · Computer Science 2025-12-01 Neemesh Yadav , Francesco Ortu , Jiarui Liu , Joeun Yook , Bernhard Schölkopf , Rada Mihalcea , Alberto Cazzaniga , Zhijing Jin

While large language models (LLMs) have increasingly been applied to hate speech detoxification, the prompts often trigger safety alerts, causing LLMs to refuse the task. In this study, we systematically investigate false refusal behavior…

Computation and Language · Computer Science 2026-01-14 Kyuri Im , Shuzhou Yuan , Michael Färber

This paper presents a systematic evaluation of Large Language Models' (LLMs) behavior on long-tail distributed (encrypted) texts and their safety implications. We introduce a two-dimensional framework for assessing LLM safety: (1)…

Computation and Language · Computer Science 2025-06-05 Utsav Maskey , Mark Dras , Usman Naseem

The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into…

Artificial Intelligence · Computer Science 2024-07-09 Lukas Struppek , Minh Hieu Le , Dominik Hintersdorf , Kristian Kersting

Guardrail, an emerging mechanism designed to ensure that large language models (LLMs) align with human values by moderating harmful or toxic responses, requires a sociotechnical approach in their design. This paper addresses a critical…

Artificial Intelligence · Computer Science 2025-06-05 Jinwei Hu , Yi Dong , Xiaowei Huang

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

Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in activation space, enabling targeted interventions to bypass…

Computation and Language · Computer Science 2026-02-26 Xinpeng Wang , Mingyang Wang , Yihong Liu , Hinrich Schütze , Barbara Plank

With the ubiquity of Large Language Models (LLMs), guardrails have become crucial to detect and defend against toxic content. However, with the increasing pervasiveness of LLMs in multilingual scenarios, their effectiveness in handling…

Computation and Language · Computer Science 2024-10-30 Yahan Yang , Soham Dan , Dan Roth , Insup Lee

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

Computation and Language · Computer Science 2025-09-29 Yahan Yang , Soham Dan , Shuo Li , Dan Roth , Insup Lee

Large language models (LLMs) acquire beliefs about gender from training data and can therefore generate text with stereotypical gender attitudes. Prior studies have demonstrated model generations favor one gender or exhibit stereotypes…

Computation and Language · Computer Science 2024-10-16 Sharon Levy , William D. Adler , Tahilin Sanchez Karver , Mark Dredze , Michelle R. Kaufman

While the biases of language models in production are extensively documented, the biases of their guardrails have been neglected. This paper studies how contextual information about the user influences the likelihood of an LLM to refuse to…

Computation and Language · Computer Science 2025-08-27 Victoria R. Li , Yida Chen , Naomi Saphra

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

Improvements in model construction, including fortified safety guardrails, allow Large language models (LLMs) to increasingly pass standard safety checks. However, LLMs sometimes slip into revealing harmful behavior, such as expressing…

Computation and Language · Computer Science 2025-10-14 Nafiseh Nikeghbal , Amir Hossein Kargaran , Jana Diesner

In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as "safeguards" or "guardrails", has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This…

Cryptography and Security · Computer Science 2024-06-06 Yi Dong , Ronghui Mu , Yanghao Zhang , Siqi Sun , Tianle Zhang , Changshun Wu , Gaojie Jin , Yi Qi , Jinwei Hu , Jie Meng , Saddek Bensalem , Xiaowei Huang

Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…

Computation and Language · Computer Science 2025-02-14 Riccardo Cantini , Giada Cosenza , Alessio Orsino , Domenico Talia
‹ Prev 1 2 3 10 Next ›