English
Related papers

Related papers: SHARP: Social Harm Analysis via Risk Profiles for …

200 papers

This research focuses on using large language models (LLMs) to simulate social experiments, exploring their ability to emulate human personality in virtual persona role-playing. The research develops an end-to-end evaluation framework,…

Computers and Society · Computer Science 2025-10-15 Yuqi Bai , Tianyu Huang , Kun Sun , Yuting Chen

Large language models (LLMs) are increasingly deployed across high-impact domains, from clinical decision support and legal analysis to hiring and education, making fairness and bias evaluation before deployment critical. However, existing…

Computation and Language · Computer Science 2025-10-17 Ali Mekky , Omar El Herraoui , Preslav Nakov , Yuxia Wang

Large language models (LLMs) have emerged as powerful tools but pose significant safety risks through harmful outputs and vulnerability to adversarial attacks. We propose SaP, short for Safety Polytope, a geometric approach to LLM safety…

Machine Learning · Computer Science 2025-06-02 Xin Chen , Yarden As , Andreas Krause

Large language models (LLMs) have demonstrated remarkable capabilities across a broad spectrum of tasks. They have attracted significant attention and been deployed in numerous downstream applications. Nevertheless, akin to a double-edged…

Computation and Language · Computer Science 2023-11-28 Zishan Guo , Renren Jin , Chuang Liu , Yufei Huang , Dan Shi , Supryadi , Linhao Yu , Yan Liu , Jiaxuan Li , Bojian Xiong , Deyi Xiong

Large Language Models (LLMs) such as Mistral and LLaMA have showcased remarkable performance across various natural language processing (NLP) tasks. Despite their success, these models inherit social biases from the diverse datasets on…

Computation and Language · Computer Science 2024-06-19 Nirmalendu Prakash , Lee Ka Wei Roy

Ensuring the safety of large language models (LLMs) is critical for responsible deployment, yet existing evaluations often prioritize performance over identifying failure modes. We introduce Phare, a multilingual diagnostic framework to…

Computers and Society · Computer Science 2025-05-27 Pierre Le Jeune , Benoît Malézieux , Weixuan Xiao , Matteo Dora

The increasing adoption of Large Language Models (LLMs) in software engineering has sparked interest in their use for software vulnerability detection. However, the rapid development of this field has resulted in a fragmented research…

Software Engineering · Computer Science 2025-12-22 Sabrina Kaniewski , Fabian Schmidt , Markus Enzweiler , Michael Menth , Tobias Heer

Large Language Models (LLMs) are increasingly integrated into safety-critical workflows, yet existing security analyses remain fragmented and often isolate model behavior from the broader system context. This work introduces a goal-driven…

Cryptography and Security · Computer Science 2026-03-10 Neha Nagaraja , Hayretdin Bahsi

The increasing use of Large Language Models (LLMs) offers significant opportunities across the engineering lifecycle, including requirements engineering, software development, process optimization, and decision support. Despite this…

Software Engineering · Computer Science 2026-02-05 Stefan Otten , Philipp Reis , Philipp Rigoll , Joshua Ransiek , Tobias Schürmann , Jacob Langner , Eric Sax

Understanding how large language models (LLMs) process emotionally sensitive content is critical for building safe and reliable systems, particularly in mental health contexts. We investigate the scaling behavior of LLMs on two key tasks:…

Computation and Language · Computer Science 2025-09-08 Edoardo Pinzuti , Oliver Tüscher , André Ferreira Castro

Recent breakthroughs in large language models (LLMs) have generated both interest and concern about their potential adoption as information sources or communication tools across different domains. In public health, where stakes are high and…

Human-Computer Interaction · Computer Science 2025-10-16 Jiawei Zhou , Amy Z. Chen , Darshi Shah , Laura M. Schwab Reese , Munmun De Choudhury

Fine-tuning Large Language Models (LLMs) has emerged as a common practice for tailoring models to individual needs and preferences. The choice of datasets for fine-tuning can be diverse, introducing safety concerns regarding the potential…

Computation and Language · Computer Science 2024-10-15 Hyeong Kyu Choi , Xuefeng Du , Yixuan Li

Large Language Models (LLMs) are typically evaluated for safety under single-shot or low-budget adversarial prompting, which underestimates real-world risk. In practice, attackers can exploit large-scale parallel sampling to repeatedly…

Artificial Intelligence · Computer Science 2026-02-10 Mingqian Feng , Xiaodong Liu , Weiwei Yang , Chenliang Xu , Christopher White , Jianfeng Gao

Large Language Models (LLMs) are acquiring a wider range of capabilities, including understanding and responding in multiple languages. While they undergo safety training to prevent them from answering illegal questions, imbalances in…

Computation and Language · Computer Science 2025-03-18 Likai Tang , Niruth Bogahawatta , Yasod Ginige , Jiarui Xu , Shixuan Sun , Surangika Ranathunga , Suranga Seneviratne

As Large Language Models (LLMs) are integrated into global software systems, ensuring equitable safety guardrails is a critical requirement. Current fairness evaluations predominantly measure bias observationally, a methodology confounded…

Artificial Intelligence · Computer Science 2026-05-08 Alif Al Hasan

Large language models (LLMs) are known to inherit and even amplify societal biases present in their pre-training corpora, threatening fairness and social trust. To address this issue, recent work has explored ``editing'' LLM parameters to…

Computation and Language · Computer Science 2025-12-03 Daiki Shirafuji , Tatsuhiko Saito , Yasutomo Kimura

Large language models (LLMs) are increasingly deployed in contexts where their failures can have direct sociopolitical consequences. Yet, existing safety benchmarks rarely test vulnerabilities in domains such as political manipulation,…

Computation and Language · Computer Science 2026-02-24 Punya Syon Pandey , Hai Son Le , Devansh Bhardwaj , Rada Mihalcea , Zhijing Jin

Large language models (LLMs) have demonstrated strong performance on coding tasks such as generation, completion and repair, but their ability to handle complex symbolic reasoning over code still remains underexplored. We introduce the task…

Software Engineering · Computer Science 2025-09-17 Daniel Koh , Yannic Noller , Corina S. Pasareanu , Adrians Skapars , Youcheng Sun

Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world. However, LLMs can capture social biases from unprocessed training data and propagate the biases to downstream…

Computation and Language · Computer Science 2024-02-22 Yingji Li , Mengnan Du , Rui Song , Xin Wang , Ying Wang

Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretability, but creates a propagation risk: a bounded perturbation to one component can be reused…

Cryptography and Security · Computer Science 2026-05-28 Md Hafizur Rahman , Zafaryab Haider , Tanzim Mahfuz , Prabuddha Chakraborty