English
Related papers

Related papers: Panacea: Pareto Alignment via Preference Adaptatio…

200 papers

Large language model (LLM) alignment faces a critical dilemma when addressing multiple human preferences: improvements in one dimension frequently come at the expense of others, creating unavoidable trade-offs between competing objectives…

Large language models (LLMs) can handle a wide variety of general tasks with simple prompts, without the need for task-specific training. Multimodal Large Language Models (MLLMs), built upon LLMs, have demonstrated impressive potential in…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Tao Yu , Yi-Fan Zhang , Chaoyou Fu , Junkang Wu , Jinda Lu , Kun Wang , Xingyu Lu , Yunhang Shen , Guibin Zhang , Dingjie Song , Yibo Yan , Tianlong Xu , Qingsong Wen , Zhang Zhang , Yan Huang , Liang Wang , Tieniu Tan

With the rapid advancement of large language models (LLMs), aligning them with human values for safety and ethics has become a critical challenge. This problem is especially challenging when multiple, potentially conflicting human values…

Machine Learning · Computer Science 2025-11-25 Hefei Xu , Le Wu , Chen Cheng , Hao Liu

Existing preference optimization objectives for language model alignment require additional hyperparameters that must be extensively tuned to achieve optimal performance, increasing both the complexity and time required for fine-tuning…

Machine Learning · Computer Science 2025-02-21 Teng Xiao , Yige Yuan , Zhengyu Chen , Mingxiao Li , Shangsong Liang , Zhaochun Ren , Vasant G Honavar

Fine-tuning large language models (LLMs) to align with human preferences has driven the success of systems such as Gemini and ChatGPT. However, approaches like Reinforcement Learning from Human Feedback (RLHF) remain computationally…

Machine Learning · Computer Science 2026-05-25 Miria Feng , Mert Pilanci

Domain adaptation (DA) attempts to transfer the knowledge from a labeled source domain to an unlabeled target domain that follows different distribution from the source. To achieve this, DA methods include a source classification objective…

Machine Learning · Computer Science 2021-12-10 Fangrui Lv , Jian Liang , Kaixiong Gong , Shuang Li , Chi Harold Liu , Han Li , Di Liu , Guoren Wang

Reward models (RMs) are essential for aligning large language models (LLMs) with human preferences to improve interaction quality. However, the real world is pluralistic, which leads to diversified human preferences with respect to…

Computation and Language · Computer Science 2023-09-18 Pengyu Cheng , Jiawen Xie , Ke Bai , Yong Dai , Nan Du

Multi-objective alignment from human feedback (MOAHF) in large language models (LLMs) is a challenging problem as human preferences are complex, multifaceted, and often conflicting. Recent works on MOAHF considered a-priori multi-objective…

Machine Learning · Computer Science 2024-12-10 Subhojyoti Mukherjee , Anusha Lalitha , Sailik Sengupta , Aniket Deshmukh , Branislav Kveton

Large Language Models (LLMs) are integral to applications such as conversational agents and content creation, where precise control over a model's personality is essential for maintaining tone, consistency, and user engagement. However,…

Computation and Language · Computer Science 2026-01-22 Seojin Hwang , Yumin Kim , Byeongjeong Kim , Donghoon Shin , Hwanhee Lee

In the field of large language models (LLMs), aligning models with the diverse preferences of users is a critical challenge. Direct Preference Optimization (DPO) has played a key role in this area. It works by using pairs of preferences…

Computation and Language · Computer Science 2024-05-29 Yueqin Yin , Zhendong Wang , Yi Gu , Hai Huang , Weizhu Chen , Mingyuan Zhou

Reinforcement Learning from Human Feedback (RLHF) effectively aligns Large Language Models (LLMs) with aggregate human preferences but often fails to address the diverse and conflicting needs of individual users. To overcome this issue, we…

Machine Learning · Computer Science 2026-05-21 Yinlam Chow , Guy Tennenholtz , Ted Yun , James Harrison , Arthur Gretton , Andre Barreto , Bo Dai

Multi-task trade-offs in machine learning can be addressed via Pareto Front Learning (PFL) methods that parameterize the Pareto Front (PF) with a single model. PFL permits to select the desired operational point during inference, contrary…

Machine Learning · Computer Science 2025-02-27 Nikolaos Dimitriadis , Pascal Frossard , Francois Fleuret

Automated negotiation in complex, multi-party and multi-issue settings critically depends on accurate opponent modeling. However, conventional numerical-only approaches fail to capture the qualitative information embedded in natural…

After pre-training, large language models are aligned with human preferences based on pairwise comparisons. State-of-the-art alignment methods (such as PPO-based RLHF and DPO) are built on the assumption of aligning with a single preference…

Machine Learning · Computer Science 2025-05-30 Paul Gölz , Nika Haghtalab , Kunhe Yang

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

Computation and Language · Computer Science 2023-10-03 Tianci Xue , Ziqi Wang , Heng Ji

The alignment of large language models (LLMs) with human values increasingly relies on using other LLMs as automated judges, or ``autoraters''. However, their reliability is limited by a foundational issue: they are trained on discrete…

Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values to ensure secure AI systems. Reinforcement learning from human feedback (RLHF) has been employed to achieve this alignment.…

Computation and Language · Computer Science 2024-02-28 Feifan Song , Bowen Yu , Minghao Li , Haiyang Yu , Fei Huang , Yongbin Li , Houfeng Wang

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

Finding specific preference-guided Pareto solutions that represent different trade-offs among multiple objectives is critical yet challenging in multi-objective problems. Existing methods are restrictive in preference definitions and/or…

Machine Learning · Computer Science 2025-03-28 Lisha Chen , AFM Saif , Yanning Shen , Tianyi Chen

Inference-time alignment enables large language models (LLMs) to generate outputs aligned with end-user preferences without further training. Recent post-training methods achieve this by using small guidance models to modify token…

Artificial Intelligence · Computer Science 2025-11-14 Sarat Chandra Bobbili , Ujwal Dinesha , Dheeraj Narasimha , Srinivas Shakkottai