English
Related papers

Related papers: Adaptive Helpfulness-Harmlessness Alignment with P…

200 papers

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their transition to real-world applications reveals a critical limitation: the inability to adapt to individual preferences while maintaining alignment with…

Computation and Language · Computer Science 2025-05-06 Jian Guan , Junfei Wu , Jia-Nan Li , Chuanqi Cheng , Wei Wu

Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives simultaneously. Existing methods predominantly rely on static preference weight…

Machine Learning · Computer Science 2026-04-28 Wenzhe Xu , Biao Liu , Yiyang Sun , Xin Geng , Ning Xu

Large language models are first pre-trained on trillions of tokens and then instruction-tuned or aligned to specific preferences. While pre-training remains out of reach for most researchers due to the compute required, fine-tuning has…

Computation and Language · Computer Science 2024-06-10 Megh Thakkar , Quentin Fournier , Matthew D Riemer , Pin-Yu Chen , Amal Zouaq , Payel Das , Sarath Chandar

Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remains comparatively underexplored. Similar to language models,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-03 Elmira Amirloo , Jean-Philippe Fauconnier , Christoph Roesmann , Christian Kerl , Rinu Boney , Yusu Qian , Zirui Wang , Afshin Dehghan , Yinfei Yang , Zhe Gan , Peter Grasch

Direct Preference Optimization (DPO) has emerged as an important approach for learning from human preferences in aligning large language models (LLMs). However, collecting human preference data is costly and inefficient, motivating methods…

Computation and Language · Computer Science 2025-12-01 Jiacheng Guo , Zihao Li , Jiahao Qiu , Yue Wu , Mengdi Wang

Large language models (LLMs), despite their extensive pretraining on diverse datasets, require effective alignment to human preferences for practical and reliable deployment. Conventional alignment methods typically employ off-policy…

Computation and Language · Computer Science 2025-07-29 Hyeonji Lee , Daejin Jo , Seohwan Yun , Sungwoong Kim

Recent advances in large language models (LLMs) have significantly improved the alignment of models with general human preferences. However, a major challenge remains in adapting LLMs to individual preferences, which are not only diverse…

Computation and Language · Computer Science 2026-04-15 Shanyong Wang , Shuhang Lin , Yining Zhao , Xi Zhu , Yongfeng Zhang

Learning from human feedback (LHF) -- and in particular learning from pairwise preferences -- has recently become a crucial ingredient in training large language models (LLMs), and has been the subject of much research. Most recent works…

Machine Learning · Computer Science 2024-01-11 Vincent Dumoulin , Daniel D. Johnson , Pablo Samuel Castro , Hugo Larochelle , Yann Dauphin

In classic reinforcement learning (RL) and decision making problems, policies are evaluated with respect to a scalar reward function, and all optimal policies are the same with regards to their expected return. However, many real-world…

Machine Learning · Computer Science 2023-11-02 Han Shao , Lee Cohen , Avrim Blum , Yishay Mansour , Aadirupa Saha , Matthew R. Walter

Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. However, analyzing live dialogues in real-time necessitates low-latency processing…

Computation and Language · Computer Science 2025-03-10 Xuanqing Liu , Luyang Kong , Wei Niu , Afshin Khashei , Belinda Zeng , Steve Johnson , Jon Jay , Davor Golac , Matt Pope

In social impact optimization, AI decision systems often rely on solvers that optimize well-calibrated mathematical objectives. However, these solvers cannot directly accommodate evolving human preferences, typically expressed in natural…

Artificial Intelligence · Computer Science 2025-09-23 Guojun Xiong , Milind Tambe

Large Language Models (LLM) alignment aims to prevent models from producing content that misaligns with human expectations, which can lead to ethical and legal concerns. In the last few years, Reinforcement Learning from Human Feedback…

Computation and Language · Computer Science 2024-10-10 Biao Liu , Ning Xu , Xin Geng

Reinforcement learning from human feedback (RLHF) has emerged as a central framework for aligning large language models (LLMs) with human preferences. Despite its practical success, RLHF raises fundamental statistical questions because it…

Machine Learning · Statistics 2026-04-06 Pangpang Liu , Chengchun Shi , Will Wei Sun

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

Recent studies have shown that large language models' (LLMs) mathematical problem-solving capabilities can be enhanced by integrating external tools, such as code interpreters, and employing multi-turn Chain-of-Thought (CoT) reasoning.…

Large language models (LLMs) have shown great potential in natural language processing tasks, but their application to machine translation (MT) remains challenging due to pretraining on English-centric data and the complexity of…

Computation and Language · Computer Science 2025-01-24 Guofeng Cui , Pichao Wang , Yang Liu , Zemian Ke , Zhu Liu , Vimal Bhat

Personalized algorithms can inadvertently expose users to discomforting recommendations, potentially triggering negative consequences. The subjectivity of discomfort and the black-box nature of these algorithms make it challenging to…

Information Retrieval · Computer Science 2025-01-24 Jiahao Liu , Yiyang Shao , Peng Zhang , Dongsheng Li , Hansu Gu , Chao Chen , Longzhi Du , Tun Lu , Ning Gu

Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited. In this work, we study the…

Machine Learning · Computer Science 2024-11-01 Angelica Chen , Sadhika Malladi , Lily H. Zhang , Xinyi Chen , Qiuyi Zhang , Rajesh Ranganath , Kyunghyun Cho

Large language models (LLMs) have shown promising abilities as cost-effective and reference-free evaluators for assessing language generation quality. In particular, pairwise LLM evaluators, which compare two generated texts and determine…

Computation and Language · Computer Science 2024-10-15 Han Zhou , Xingchen Wan , Yinhong Liu , Nigel Collier , Ivan Vulić , Anna Korhonen

With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from Human Feedback (RLHF) has been adopted to enhance the…

Artificial Intelligence · Computer Science 2026-03-25 Shiji Zhao , Mengyang Wang , Shukun Xiong , Fangzhou Chen , Qihui Zhu , Shouwei Ruan , Yisong Xiao , Ranjie Duan , Xun Chen , XingXing Wei