English
Related papers

Related papers: Understanding Likelihood Over-optimisation in Dire…

200 papers

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Computation and Language · Computer Science 2025-10-31 Xuandong Zhao , Will Cai , Tianneng Shi , David Huang , Licong Lin , Song Mei , Dawn Song

Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance can be limited by the quality of the training data and its…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Amirabbas Afzali , Borna Khodabandeh , Ali Rasekh , Mahyar JafariNodeh , Sepehr kazemi , Simon Gottschalk

Large Language Models (LLMs) suffer from order bias, where their performance is affected by the arrangement order of input elements. This unfairness limits the model's applications in scenarios such as in-context learning and…

Machine Learning · Computer Science 2026-05-13 Xu Chu , Guanyu Wang , Zhijie Tan , Xinrong Chen , Ziyu Li , Tong Mo , Weiping Li

Offline preference alignment for language models such as Direct Preference Optimization (DPO) is favored for its effectiveness and simplicity, eliminating the need for costly reinforcement learning. Various offline algorithms have been…

Machine Learning · Computer Science 2025-07-28 Junbo Li , Zhangyang Wang , Qiang Liu

While alignment algorithms are now commonly used to tune pre-trained language models towards a user's preferences, we lack explanations for the underlying mechanisms in which models become ``aligned'', thus making it difficult to explain…

Computation and Language · Computer Science 2024-01-05 Andrew Lee , Xiaoyan Bai , Itamar Pres , Martin Wattenberg , Jonathan K. Kummerfeld , Rada Mihalcea

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

Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Bram Wallace , Meihua Dang , Rafael Rafailov , Linqi Zhou , Aaron Lou , Senthil Purushwalkam , Stefano Ermon , Caiming Xiong , Shafiq Joty , Nikhil Naik

Direct Preference Optimization (DPO) has emerged as a stable, scalable, and efficient solution for language model alignment. Despite its empirical success, the optimization properties, particularly the impact of samplers on its convergence…

Machine Learning · Computer Science 2025-02-04 Ruizhe Shi , Runlong Zhou , Simon S. Du

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

Ensuring AI models align with human values is essential for their safety and functionality. Reinforcement learning from human feedback (RLHF) leverages human preferences to achieve this alignment. However, when preferences are sourced from…

Machine Learning · Computer Science 2025-02-10 Ryan Bahlous-Boldi , Li Ding , Lee Spector , Scott Niekum

Aligning Large Language Models (LLMs) with human preferences is crucial for safe and effective AI interactions. While popular methods like Direct Preference Optimization (DPO) have simplified alignment, they remain sensitive to data noise…

Artificial Intelligence · Computer Science 2026-03-03 Ning Yang , Hai Lin , Yibo Liu , Baoliang Tian , Guoqing Liu , Haijun Zhang

The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios, there are still many challenges in improving the reasoning…

Artificial Intelligence · Computer Science 2024-12-25 Jiacai Liu , Chaojie Wang , Chris Yuhao Liu , Liang Zeng , Rui Yan , Yiwen Sun , Yang Liu , Yahui Zhou

Direct Preference Optimization (DPO) has become a popular method for fine-tuning large language models (LLMs) due to its stability and simplicity. However, it is also known to be sensitive to noise in the data and prone to overfitting.…

Machine Learning · Computer Science 2025-10-28 Cheol Woo Kim , Shresth Verma , Mauricio Tec , Milind Tambe

Multimodal Large Language Models (MLLMs) are known to hallucinate, which limits their practical applications. Recent works have attempted to apply Direct Preference Optimization (DPO) to enhance the performance of MLLMs, but have shown…

Computation and Language · Computer Science 2024-11-18 Yuhan Fu , Ruobing Xie , Xingwu Sun , Zhanhui Kang , Xirong Li

As large language models (LLMs) see greater use in academic and commercial settings, there is increasing interest in methods that allow language models to generate texts aligned with human preferences. In this paper, we present an initial…

Machine Learning · Computer Science 2024-06-07 Victoria Lin , Eli Ben-Michael , Louis-Philippe Morency

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

Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in aligning English LLMs, multilingual preference alignment is…

Computation and Language · Computer Science 2025-06-06 Wen Yang , Junhong Wu , Chen Wang , Chengqing Zong , Jiajun Zhang

A major challenge in aligning large language models (LLMs) with human preferences is the issue of distribution shift. LLM alignment algorithms rely on static preference datasets, assuming that they accurately represent real-world user…

Machine Learning · Computer Science 2026-01-16 Zaiyan Xu , Sushil Vemuri , Kishan Panaganti , Dileep Kalathil , Rahul Jain , Deepak Ramachandran

Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. While DPO establishes an offline paradigm with single…

Machine Learning · Computer Science 2025-10-28 Junkang Wu , Kexin Huang , Xue Wang , Jinyang Gao , Bolin Ding , Jiancan Wu , Xiangnan He , Xiang Wang

Aligning language models (LMs) with curated human feedback is critical to control their behaviors in real-world applications. Several recent policy optimization methods, such as DPO and SLiC, serve as promising alternatives to the…

Computation and Language · Computer Science 2025-01-28 Tianqi Liu , Zhen Qin , Junru Wu , Jiaming Shen , Misha Khalman , Rishabh Joshi , Yao Zhao , Mohammad Saleh , Simon Baumgartner , Jialu Liu , Peter J. Liu , Xuanhui Wang
‹ Prev 1 8 9 10 Next ›