English
Related papers

Related papers: Navigating the OverKill in Large Language Models

200 papers

Large language models (LLMs) have achieved state-of-the-art performance on a series of natural language understanding tasks. However, these LLMs might rely on dataset bias and artifacts as shortcuts for prediction. This has significantly…

Computation and Language · Computer Science 2023-05-09 Mengnan Du , Fengxiang He , Na Zou , Dacheng Tao , Xia Hu

Recent work on test-time scaling for large language model (LLM) reasoning typically assumes that allocating more inference-time computation uniformly improves correctness. However, prior studies show that reasoning uncertainty is highly…

Computation and Language · Computer Science 2026-02-23 Lexiang Tang , Weihao Gao , Bingchen Zhao , Lu Ma , Qiao jin , Bang Yang , Yuexian Zou

Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs. While significant research focuses on mitigating harmful content generation, the enhanced safety often come with the side effect of over-refusal,…

Computation and Language · Computer Science 2025-06-17 Justin Cui , Wei-Lin Chiang , Ion Stoica , Cho-Jui Hsieh

Self-preference is a fundamental feature of biological organisms. Since large language models (LLMs) lack sentience, they might be expected to avoid such distortions. Yet, across 72 experiments and ~41,000 queries, we discovered massive…

Artificial Intelligence · Computer Science 2026-05-20 Steven A. Lehr , Mary Cipperman , Mahzarin R. Banaji

Large Language Models (LLMs) rely on various decoding strategies to generate text, and these choices can significantly affect output quality. In healthcare, where accuracy is critical, the impact of decoding strategies remains…

Computation and Language · Computer Science 2025-08-20 Oriana Presacan , Alireza Nik , Vajira Thambawita , Bogdan Ionescu , Michael Riegler

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

Computation and Language · Computer Science 2023-08-28 Aibek Bekbayev , Sungbae Chun , Yerzat Dulat , James Yamazaki

While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints. A growing line of work addresses this problem by modifying the model's sampling policy at decoding time using…

Machine Learning · Computer Science 2026-05-15 Bat-Sheva Einbinder , Hen Davidov , Yee Whye Teh , Yarin Gal , Yaniv Romano

Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its…

Machine Learning · Computer Science 2024-11-01 Andy Arditi , Oscar Obeso , Aaquib Syed , Daniel Paleka , Nina Panickssery , Wes Gurnee , Neel Nanda

Large language models (LLMs) have demonstrated impressive performance on a number of natural language processing tasks, such as question answering and text summarization. However, their performance on sequence labeling tasks such as intent…

Computation and Language · Computer Science 2024-02-27 Yao Qiang , Subhrangshu Nandi , Ninareh Mehrabi , Greg Ver Steeg , Anoop Kumar , Anna Rumshisky , Aram Galstyan

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

Natural Language Inference (NLI) models are known to learn from biases and artefacts within their training data, impacting how well they generalise to other unseen datasets. Existing de-biasing approaches focus on preventing the models from…

Computation and Language · Computer Science 2022-05-03 Joe Stacey , Yonatan Belinkov , Marek Rei

Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application. In this paper, we conduct extensive experiments to study this phenomenon. We analyze the impact of…

Computation and Language · Computer Science 2022-03-08 Canwen Xu , Zexue He , Zhankui He , Julian McAuley

While instruction-tuned language models have demonstrated impressive zero-shot generalization, these models often struggle to generate accurate responses when faced with instructions that fall outside their training set. This paper presents…

Computation and Language · Computer Science 2024-02-20 Taehyeon Kim , Joonkee Kim , Gihun Lee , Se-Young Yun

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…

Computation and Language · Computer Science 2024-02-20 Kai Chen , Chunwei Wang , Kuo Yang , Jianhua Han , Lanqing Hong , Fei Mi , Hang Xu , Zhengying Liu , Wenyong Huang , Zhenguo Li , Dit-Yan Yeung , Lifeng Shang , Xin Jiang , Qun Liu

Large language models often generate confident but incorrect answers rather than abstaining when uncertain. This problem is particularly acute for small language models (SLMs), where computational constraints and autonomous operation…

Artificial Intelligence · Computer Science 2026-05-26 Ashwath Vaithinathan Aravindan , Mayank Kejriwal

Large Language Models (LLMs) like OpenAI's GPT series, Anthropic's Claude, and Meta's LLaMa have shown remarkable capabilities in text generation. However, their susceptibility to toxic prompts presents significant security challenges. This…

Cryptography and Security · Computer Science 2024-12-03 Jie Li , Yi Liu , Chongyang Liu , Xiaoning Ren , Ling Shi , Weisong Sun , Yinxing Xue

The past a few years have witnessed the great success of large language models, demonstrating powerful capabilities in comprehending textual data and generating human-like languages. Large language models achieve success by being trained on…

Computation and Language · Computer Science 2025-03-20 Estrid He , Tabinda Sarwar , Ibrahim Khalil , Xun Yi , Ke Wang

In this study, we tackle a growing concern around the safety and ethical use of large language models (LLMs). Despite their potential, these models can be tricked into producing harmful or unethical content through various sophisticated…

Computation and Language · Computer Science 2024-11-19 Somnath Banerjee , Sayan Layek , Rima Hazra , Animesh Mukherjee

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

The widespread adoption of Large Language Models (LLMs) has become commonplace, particularly with the emergence of open-source models. More importantly, smaller models are well-suited for integration into consumer devices and are frequently…

Computation and Language · Computer Science 2024-08-16 Aisha Khatun , Daniel G. Brown
‹ Prev 1 3 4 5 6 7 10 Next ›