English
Related papers

Related papers: ProSocialAlign: Preference Conditioned Test Time A…

200 papers

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Cryptography and Security · Computer Science 2025-05-30 Jinchuan Zhang , Lu Yin , Yan Zhou , Songlin Hu

Most existing dialogue systems fail to respond properly to potentially unsafe user utterances by either ignoring or passively agreeing with them. To address this issue, we introduce ProsocialDialog, the first large-scale multi-turn dialogue…

Computation and Language · Computer Science 2022-10-26 Hyunwoo Kim , Youngjae Yu , Liwei Jiang , Ximing Lu , Daniel Khashabi , Gunhee Kim , Yejin Choi , Maarten Sap

Safety alignment is an essential research topic for real-world AI applications. Despite the multifaceted nature of safety and trustworthiness in AI, current safety alignment methods often focus on a comprehensive notion of safety. By…

Artificial Intelligence · Computer Science 2025-02-05 Thien Q. Tran , Akifumi Wachi , Rei Sato , Takumi Tanabe , Youhei Akimoto

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Xingyu Zhu , Beier Zhu , Junfeng Fang , Shuo Wang , Yin Zhang , Xiang Wang , Xiangnan He

Language model benchmarks are pervasive and computationally-efficient proxies for real-world performance. However, many recent works find that benchmarks often fail to predict real utility. Towards bridging this gap, we introduce benchmark…

Artificial Intelligence · Computer Science 2026-05-28 Marco Gutierrez , Xinyi Leng , Hannah Cyberey , Jonathan Richard Schwarz , Ahmed Alaa , Thomas Hartvigsen

Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive or controversial questions. However, with the rapid…

Computation and Language · Computer Science 2025-03-31 Yazhou Zhang , Qimeng Liu , Qiuchi Li , Peng Zhang , Jing Qin

Speech language models have significantly advanced in generating realistic speech, with neural codec language models standing out. However, the integration of human feedback to align speech outputs to human preferences is often neglected.…

Computation and Language · Computer Science 2024-04-09 Dong Zhang , Zhaowei Li , Shimin Li , Xin Zhang , Pengyu Wang , Yaqian Zhou , Xipeng Qiu

Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the overrefusal problem…

Artificial Intelligence · Computer Science 2026-03-13 Zhiyu Xue , Zimo Qi , Guangliang Liu , Bocheng Chen , Ramtin Pedarsani

Reward Modeling is critical in evaluating and improving the generation of Large Language Models (LLMs). While numerous recent works have shown its feasibility in improving safety, helpfulness, reasoning, and instruction-following ability,…

Computation and Language · Computer Science 2025-11-13 Hanning Zhang , Juntong Song , Juno Zhu , Yuanhao Wu , Tong Zhang , Cheng Niu

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Cryptography and Security · Computer Science 2025-06-02 Jianwei Li , Jung-Eun Kim

We study the problem of aligning a generative model's response with a user's preferences. Recent works have proposed several different formulations for personalized alignment; however, they either require a large amount of user preference…

Machine Learning · Computer Science 2025-11-06 Victor-Alexandru Pădurean , Parameswaran Kamalaruban , Nachiket Kotalwar , Alkis Gotovos , Adish Singla

While recent code-specific large language models (LLMs) have greatly enhanced their code generation capabilities, the safety of these models remains under-explored, posing potential risks as insecure code generated by these models may…

Cryptography and Security · Computer Science 2025-06-09 Xiangzhe Xu , Zian Su , Jinyao Guo , Kaiyuan Zhang , Zhenting Wang , Xiangyu Zhang

Increasing test-time computation has emerged as a promising direction for improving language model performance, particularly in scenarios where model finetuning is impractical or impossible due to computational constraints or private model…

Computation and Language · Computer Science 2025-12-22 Gonçalo Faria , Noah A. Smith

Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…

Artificial Intelligence · Computer Science 2026-05-12 Katarzyna Kobalczyk , Mihaela van der Schaar

Alignment of Large Language Models (LLMs) remains an unsolved problem. Human preferences are highly distributed and can be captured at multiple levels of abstraction, from the individual to diverse populations. Organisational preferences,…

Machine Learning · Computer Science 2024-08-02 Gareth Seneque , Lap-Hang Ho , Ariel Kuperman , Nafise Erfanian Saeedi , Jeffrey Molendijk

Detecting prosociality in text--communication intended to affirm, support, or improve others' behavior--is a novel and increasingly important challenge for trust and safety systems. Unlike toxic content detection, prosociality lacks…

Computation and Language · Computer Science 2025-08-11 Rafal Kocielnik , Min Kim , Penphob , Boonyarungsrit , Fereshteh Soltani , Deshawn Sambrano , Animashree Anandkumar , R. Michael Alvarez

Ensuring safe and contextually appropriate behaviour in Large Language Models (LLMs) remains a critical challenge for real-world deployment. We present \textbf{SafeCtrl-RL}, an inference-time behavioural control framework that enables…

Computation and Language · Computer Science 2026-05-26 Michael Orme , Yanchao Yu , Zhiyuan Tan

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…

Computation and Language · Computer Science 2025-04-07 Jaymari Chua , Chen Wang , Lina Yao

Recent AI agents, such as ChatGPT and LLaMA, primarily rely on instruction tuning and reinforcement learning to calibrate the output of large language models (LLMs) with human intentions, ensuring the outputs are harmless and helpful.…

Computation and Language · Computer Science 2025-02-14 Jingxin Xu , Guoshun Nan , Sheng Guan , Sicong Leng , Yilian Liu , Zixiao Wang , Yuyang Ma , Zhili Zhou , Yanzhao Hou , Xiaofeng Tao

Large language models~(LLMs) are expected to be helpful, harmless, and honest. In different alignment scenarios, such as safety, confidence, and general preference alignment, binary preference data collection and reward modeling are…

Computation and Language · Computer Science 2025-10-14 Shuai Zhao , Yunqiu Xu , Linchao Zhu , Yi Yang