English
Related papers

Related papers: Decoding-Time Language Model Alignment with Multip…

200 papers

Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static and homogeneous across individuals, so that aligning to a a…

Large vision-language models (LVLMs) have demonstrated remarkable capabilities by integrating pre-trained vision encoders with large language models (LLMs). Similar to single-modal LLMs, chain-of-thought (CoT) prompting has been adapted for…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Shin'ya Yamaguchi , Kosuke Nishida , Daiki Chijiwa

Despite emerging research on Language Models (LM), few approaches analyse the invertibility of LMs. That is, given a LM and a desirable target output sequence of tokens, determining what input prompts would yield the target output remains…

Computation and Language · Computer Science 2026-02-12 Kevin Yandoka Denamganaï , Kartic Subr

Aligning Large Language Models (LLMs) with human preferences is critical, yet traditional fine-tuning methods are computationally expensive and inflexible. While test-time alignment offers a promising alternative, existing approaches often…

Artificial Intelligence · Computer Science 2026-01-16 Tiesunlong Shen , Rui Mao , Jin Wang , Heming Sun , Jian Zhang , Xuejie Zhang , Erik Cambria

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 objectives is crucial for real-world applications. However, fine-tuning LLMs for alignment often suffers from unstable training and requires substantial computing resources. Test-time…

Artificial Intelligence · Computer Science 2024-11-05 Lingkai Kong , Haorui Wang , Wenhao Mu , Yuanqi Du , Yuchen Zhuang , Yifei Zhou , Yue Song , Rongzhi Zhang , Kai Wang , Chao Zhang

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

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…

Computation and Language · Computer Science 2024-08-30 Davis Yoshida

Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. This alignment process often requires only a small amount of data to…

Language models (LMs) are pretrained to imitate internet text, including content that would violate human preferences if generated by an LM: falsehoods, offensive comments, personally identifiable information, low-quality or buggy code, and…

Computation and Language · Computer Science 2023-06-16 Tomasz Korbak , Kejian Shi , Angelica Chen , Rasika Bhalerao , Christopher L. Buckley , Jason Phang , Samuel R. Bowman , Ethan Perez

Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model…

Machine Learning · Computer Science 2025-10-02 Yiran Shen , Yu Xia , Jonathan Chang , Prithviraj Ammanabrolu

Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a…

Aligning large language models (LLMs) to human preferences is challenging in domains where preference data is unavailable. We address the problem of learning reward models for such target domains by leveraging feedback collected from…

Machine Learning · Computer Science 2025-01-03 David Wu , Sanjiban Choudhury

Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rely on synthetic data generated by LLMs for scalability and…

Computation and Language · Computer Science 2025-10-21 Mingye Zhu , Yi Liu , Zheren Fu , Yongdong Zhang , Zhendong Mao

Decoding strategies largely determine the quality of Large Language Model (LLM) outputs, yet widely used heuristics such as greedy or fixed temperature/top-p decoding are static and often task-agnostic, leading to suboptimal or inconsistent…

Computation and Language · Computer Science 2026-03-20 Asmita Bhardwaj , Yuya Jeremy Ong , Eelaaf Zahid , Basel Shbita

With the rapidly expanding landscape of large language models, aligning model generations with human values and preferences is becoming increasingly important. Popular alignment methods, such as Reinforcement Learning from Human Feedback,…

Computation and Language · Computer Science 2025-02-21 Mingye Zhu , Yi Liu , Lei Zhang , Junbo Guo , Zhendong Mao

Post-training of LLMs with RLHF, and subsequently preference optimization algorithms such as DPO, IPO, etc., made a big difference in improving human alignment. However, all such techniques can only work with a single (human) objective. In…

Machine Learning · Computer Science 2025-05-19 Akhil Agnihotri , Rahul Jain , Deepak Ramachandran , Zheng Wen

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

The task of multi-objective alignment aims at balancing and controlling the different alignment objectives (e.g., helpfulness, harmlessness and honesty) of large language models to meet the personalized requirements of different users.…

Computation and Language · Computer Science 2024-08-12 Tingchen Fu , Yupeng Hou , Julian McAuley , Rui Yan

Multi-objective optimization is a common problem in practical applications, and multi-objective evolutionary algorithm (MOEA) is considered as one of the effective methods to solve these problems. However, their randomness sometimes…

Neural and Evolutionary Computing · Computer Science 2024-10-04 Wanyi Liu , Long Chen , Zhenzhou Tang