English
Related papers

Related papers: MPO: Multilingual Safety Alignment via Reward Gap …

200 papers

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Computation and Language · Computer Science 2025-05-20 Zae Myung Kim , Chanwoo Park , Vipul Raheja , Suin Kim , Dongyeop Kang

Aligning large language models (LLMs) with human values and safety constraints is challenging, especially when objectives like helpfulness, truthfulness, and avoidance of harm conflict. Reinforcement Learning from Human Feedback (RLHF) has…

Computation and Language · Computer Science 2025-03-31 Xuying Li , Zhuo Li , Yuji Kosuga , Victor Bian

Large Language Models (LLMs) have become increasingly popular due to their ability to process and generate natural language. However, as they are trained on massive datasets of text, LLMs can inherit harmful biases and produce outputs that…

Computation and Language · Computer Science 2025-01-23 Qi Gou , Cam-Tu Nguyen

Though reasoning abilities are considered language-agnostic, existing LLMs exhibit inconsistent reasoning abilities across different languages, e.g., reasoning in the dominant language like English is superior to other languages due to the…

Computation and Language · Computer Science 2024-04-16 Shuaijie She , Wei Zou , Shujian Huang , Wenhao Zhu , Xiang Liu , Xiang Geng , Jiajun Chen

The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces…

Fine-tuning large language models (LLMs) on human preferences, typically through reinforcement learning from human feedback (RLHF), has proven successful in enhancing their capabilities. However, ensuring the safety of LLMs during…

Artificial Intelligence · Computer Science 2025-04-09 Wenxuan Zhang , Philip H. S. Torr , Mohamed Elhoseiny , Adel Bibi

Large language models (LLMs) require careful alignment to balance competing objectives - factuality, safety, conciseness, proactivity, and diversity. Existing studies focus on individual techniques or specific dimensions, lacking a holistic…

Machine Learning · Computer Science 2025-09-17 Denis Janiak , Julia Moska , Dawid Motyka , Karolina Seweryn , Paweł Walkowiak , Bartosz Żuk , Arkadiusz Janz

The widespread application of large language models (LLMs) raises increasing demands on ensuring safety or imposing constraints, such as reducing harmful content and adhering to predefined rules. While there have been several works studying…

Machine Learning · Computer Science 2026-02-13 Yihan Du , Seo Taek Kong , R. Srikant

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

Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while…

Machine Learning · Computer Science 2025-02-28 Xiyue Peng , Hengquan Guo , Jiawei Zhang , Dongqing Zou , Ziyu Shao , Honghao Wei , Xin Liu

Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning large language models (LLMs). Yet its reliance on a singular reward model often overlooks the diversity of human preferences. Recent approaches address this…

Computation and Language · Computer Science 2025-07-23 Tianze Wang , Dongnan Gui , Yifan Hu , Shuhang Lin , Linjun Zhang

Large Language Models (LLMs) have achieved state-of-the-art performance across numerous tasks. However, these advancements have predominantly benefited "first-class" languages such as English and Chinese, leaving many other languages…

Computation and Language · Computer Science 2025-02-27 Wen Yang , Junhong Wu , Chen Wang , Chengqing Zong , Jiajun Zhang

The alignment of Large Language Models (LLMs) is crucial for ensuring their safety and reliability in practical applications. Direct Preference Optimization (DPO) has emerged as an efficient method that directly optimizes models using…

Computation and Language · Computer Science 2025-10-30 Jie Sun , Junkang Wu , Jiancan Wu , Zhibo Zhu , Xingyu Lu , Jun Zhou , Lintao Ma , Xiang Wang

Safety and trustworthiness are indispensable requirements for real-world applications of AI systems using large language models (LLMs). This paper formulates human value alignment as an optimization problem of the language model policy to…

Machine Learning · Computer Science 2024-10-22 Akifumi Wachi , Thien Q. Tran , Rei Sato , Takumi Tanabe , Youhei Akimoto

Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. Its primary objective is to function as a human-centric (helpful, honest, and harmless) assistant. Alignment with humans…

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns…

Computation and Language · Computer Science 2025-01-23 Yafu Li , Xuyang Hu , Xiaoye Qu , Linjie Li , Yu Cheng

The widespread deployment of large language models (LLMs) across linguistic communities necessitates reliable multilingual safety alignment. However, recent efforts to extend alignment to other languages often require substantial resources,…

Computation and Language · Computer Science 2026-02-19 Yuyan Bu , Xiaohao Liu , ZhaoXing Ren , Yaodong Yang , Juntao Dai

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image…

Cryptography and Security · Computer Science 2025-11-18 Xuankun Rong , Wenke Huang , Tingfeng Wang , Daiguo Zhou , Bo Du , Mang Ye

Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfidence phenomenon in Large Language Models (LLMs) and show that…

Computation and Language · Computer Science 2025-03-04 Jixuan Leng , Chengsong Huang , Banghua Zhu , Jiaxin Huang

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
‹ Prev 1 2 3 10 Next ›