English
Related papers

Related papers: Language Alignment via Nash-learning and Adaptive …

200 papers

Reinforcement learning is used to align language models with human preference signals after first pre-training the model to predict the next token of text within a large corpus using likelihood maximization. Before being deployed in a…

Computation and Language · Computer Science 2024-08-30 Alec Solway

Many alignment methods, including reinforcement learning from human feedback (RLHF), rely on the Bradley-Terry reward assumption, which is not always sufficient to capture the full range and complexity of general human preferences. We…

Machine Learning · Computer Science 2025-10-15 Yixin Liu , Argyris Oikonomou , Weiqiang Zheng , Yang Cai , Arman Cohan

Recently, Large Language Models (LLMs) have shown impressive language capabilities. While most of the existing LLMs have very unbalanced performance across different languages, multilingual alignment based on translation parallel data is an…

Computation and Language · Computer Science 2024-06-19 Shimao Zhang , Changjiang Gao , Wenhao Zhu , Jiajun Chen , Xin Huang , Xue Han , Junlan Feng , Chao Deng , Shujian Huang

Conversational human-likeness plays a central role in human-AI interaction, yet it has remained difficult to define, measure, and optimize. As a result, improvements in human-like behavior are largely driven by scale or broad supervised…

Artificial Intelligence · Computer Science 2026-01-08 Masum Hasan , Junjie Zhao , Ehsan Hoque

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

Computation and Language · Computer Science 2025-09-16 Xue Zhang , Yunlong Liang , Fandong Meng , Songming Zhang , Yufeng Chen , Jinan Xu , Jie Zhou

Learning from human preferences is important for language models to match human needs and to align with human and social values. Prior works have achieved remarkable successes by learning from human feedback to understand and follow…

Machine Learning · Computer Science 2023-10-19 Hao Liu , Carmelo Sferrazza , Pieter Abbeel

Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the…

Computation and Language · Computer Science 2025-10-09 Shangjian Yin , Zhepei Wei , Xinyu Zhu , Wei-Lin Chen , Yu Meng

Aligning language models to human expectations, e.g., being helpful and harmless, has become a pressing challenge for large language models. A typical alignment procedure consists of supervised fine-tuning and preference learning. Most…

Machine Learning · Computer Science 2024-02-27 Tianchi Cai , Xierui Song , Jiyan Jiang , Fei Teng , Jinjie Gu , Guannan Zhang

Artificially intelligent agents are increasingly being integrated into human decision-making: from large language model (LLM) assistants to autonomous vehicles. These systems often optimize their individual objective, leading to conflicts,…

Machine Learning · Computer Science 2025-02-07 Juan Agustin Duque , Milad Aghajohari , Tim Cooijmans , Razvan Ciuca , Tianyu Zhang , Gauthier Gidel , Aaron Courville

Preference optimization techniques have become a standard final stage for training state-of-art large language models (LLMs). However, despite widespread adoption, the vast majority of work to-date has focused on first-class citizen…

Computation and Language · Computer Science 2024-07-04 John Dang , Arash Ahmadian , Kelly Marchisio , Julia Kreutzer , Ahmet Üstün , Sara Hooker

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

The burgeoning capabilities of large language models (LLMs) have underscored the need for alignment to ensure these models act in accordance with human values and intentions. Existing alignment frameworks present constraints either in the…

Computation and Language · Computer Science 2025-04-28 Leitian Tao , Yixuan Li

Alignment is a crucial step to enhance the instruction-following and conversational abilities of language models. Despite many recent work proposing new algorithms, datasets, and training pipelines, there is a lack of comprehensive studies…

Computation and Language · Computer Science 2024-10-04 Xiao Yu , Qingyang Wu , Yu Li , Zhou Yu

Human preference alignment can greatly enhance Multimodal Large Language Models (MLLMs), but collecting high-quality preference data is costly. A promising solution is the self-evolution strategy, where models are iteratively trained on…

Machine Learning · Computer Science 2024-12-23 Wentao Tan , Qiong Cao , Yibing Zhan , Chao Xue , Changxing Ding

Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model (RM) for on-policy learning. In this paper, we present a novel alignment framework, SELF-JUDGE that (1)…

Machine Learning · Computer Science 2024-06-26 Sangkyu Lee , Sungdong Kim , Ashkan Yousefpour , Minjoon Seo , Kang Min Yoo , Youngjae Yu

Generative artificial intelligence (Generative AI), and in particular Large Language Models (LLMs) have gained significant popularity among researchers and industrial communities, paving the way for integrating LLMs in different domains,…

Computer Science and Game Theory · Computer Science 2024-10-15 Alonso Silva

Large Language Models (LLMs) have demonstrated remarkable adaptability, showcasing their capacity to excel in tasks for which they were not explicitly trained. However, despite their impressive natural language processing (NLP)…

Computation and Language · Computer Science 2023-09-08 Supun Manathunga , Isuru Hettigoda

Reinforcement Learning from Human Feedback (RLHF) is a key method for aligning large language models (LLMs) with human preferences. However, current offline alignment approaches like DPO, IPO, and SLiC rely heavily on fixed preference…

Machine Learning · Computer Science 2024-06-25 Mucong Ding , Souradip Chakraborty , Vibhu Agrawal , Zora Che , Alec Koppel , Mengdi Wang , Amrit Bedi , Furong Huang

In game-theoretic learning, several agents are simultaneously following their individual interests, so the environment is non-stationary from each player's perspective. In this context, the performance of a learning algorithm is often…

Computer Science and Game Theory · Computer Science 2021-10-19 Yu-Guan Hsieh , Kimon Antonakopoulos , Panayotis Mertikopoulos

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…

Machine Learning · Computer Science 2024-03-19 Hao Sun