English
Related papers

Related papers: Clean First, Align Later: Benchmarking Preference …

200 papers

This paper presents a novel approach to aligning large language models (LLMs) with individual human preferences, sometimes referred to as Reinforcement Learning from \textit{Personalized} Human Feedback (RLPHF). Given stated preferences…

Artificial Intelligence · Computer Science 2024-07-08 Jin Peng Zhou , Katie Z Luo , Jingwen Gu , Jason Yuan , Kilian Q. Weinberger , Wen Sun

Large Language Models (LLMs) are expected to produce safe, helpful, and honest content during interaction with human users, but they frequently fail to align with such values when given flawed instructions, e.g., missing context, ambiguous…

Computation and Language · Computer Science 2025-08-07 Feifan Song , Bofei Gao , Yifan Song , Yi Liu , Weimin Xiong , Yuyang Song , Tianyu Liu , Guoyin Wang , Houfeng Wang

Reward models (RMs) are crucial for aligning large language models (LLMs) with human preferences. However, most RM research is centered on English and relies heavily on synthetic resources, which leads to limited and less reliable datasets…

Computation and Language · Computer Science 2025-05-27 Xueru Wen , Jie Lou , Zichao Li , Yaojie Lu , Xing Yu , Yuqiu Ji , Guohai Xu , Hongyu Lin , Ben He , Xianpei Han , Le Sun , Debing Zhang

Given the broad capabilities of large language models, it should be possible to work towards a general-purpose, text-based assistant that is aligned with human values, meaning that it is helpful, honest, and harmless. As an initial foray in…

This research paper delves into the evolving landscape of fine-tuning large language models (LLMs) to align with human users, extending beyond basic alignment to propose "personality alignment" for language models in organizational…

Human-Computer Interaction · Computer Science 2023-12-07 Byunggu Yu , Junwhan Kim

We introduce DarkBench, a comprehensive benchmark for detecting dark design patterns--manipulative techniques that influence user behavior--in interactions with large language models (LLMs). Our benchmark comprises 660 prompts across six…

Computation and Language · Computer Science 2025-03-17 Esben Kran , Hieu Minh "Jord" Nguyen , Akash Kundu , Sami Jawhar , Jinsuk Park , Mateusz Maria Jurewicz

Recent advances in Multi-modal Large Language Models (MLLMs), such as LLaVA-series models, are driven by massive machine-generated instruction-following data tuning. Such automatic instruction collection pipelines, however, inadvertently…

Artificial Intelligence · Computer Science 2025-12-05 Hongzhe Huang , Jiang Liu , Zhewen Yu , Li Cai , Dian Jiao , Wenqiao Zhang , Siliang Tang , Juncheng Li , Hao Jiang , Haoyuan Li , Yueting Zhuang

Scaling up data, parameters, and test-time computation has been the mainstream methods to improve LLM systems (LLMsys), but their upper bounds are almost reached due to the gradual depletion of high-quality data and marginal gains obtained…

Machine Learning · Computer Science 2026-05-12 Qingyao Ai , Yichen Tang , Changyue Wang , Jianming Long , Weihang Su , Yiqun Liu

The training of large language models (LLMs) is expensive. In this paper, we study data-efficient approaches for pre-training LLMs, i.e., techniques that aim to optimize the Pareto frontier of model quality and training resource/data…

In the realm of artificial intelligence, where a vast majority of data is unstructured, obtaining substantial amounts of labeled data to train supervised machine learning models poses a significant challenge. To address this, we delve into…

Machine Learning · Computer Science 2024-01-19 Natan Vidra , Thomas Clifford , Katherine Jijo , Eden Chung , Liang Zhang

Large Language Models (LLMs) excel at producing broadly relevant text, but this generality becomes a limitation when user-specific preferences are required, such as recommending restaurants or planning travel. In these scenarios, users…

Machine Learning · Computer Science 2025-10-21 Ioannis Tsaknakis , Bingqing Song , Shuyu Gan , Dongyeop Kang , Alfredo Garcia , Gaowen Liu , Charles Fleming , Mingyi Hong

Code repair is a fundamental task in software development, facilitating efficient bug resolution and software maintenance. Although large language models (LLMs) have demonstrated considerable potential in automated code repair, their…

Software Engineering · Computer Science 2026-02-27 Dekun Dai , MingWei Liu , Anji Li , Jialun Cao , Yanlin Wang , Chong Wang , Xin Peng , Zibin Zheng

We present a method and dataset for fine-tuning language models with preference supervision using feedback-driven improvement chains. Given a model response, an annotator provides fine-grained feedback by marking ``liked'' and ``disliked''…

Computation and Language · Computer Science 2025-12-30 Sky CH-Wang , Justin Svegliato , Helen Appel , Jason Eisner

The advent of Large Language Models (LLMs) holds promise for revolutionizing various fields traditionally dominated by human expertise. Urban planning, a professional discipline that fundamentally shapes our daily surroundings, is one such…

Computation and Language · Computer Science 2025-05-01 Yu Zheng , Longyi Liu , Yuming Lin , Jie Feng , Guozhen Zhang , Depeng Jin , Yong Li

Large language models (LLMs) are initially pretrained for broad capabilities and then finetuned with instruction-following datasets to improve their performance in interacting with humans. Despite advances in finetuning, a standardized…

Computation and Language · Computer Science 2024-07-30 Yihan Cao , Yanbin Kang , Chi Wang , Lichao Sun

Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LLM on all existing instructions may not be optimal and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Yulei Qin , Yuncheng Yang , Pengcheng Guo , Gang Li , Hang Shao , Yuchen Shi , Zihan Xu , Yun Gu , Ke Li , Xing Sun

As LLMs become capable of complex tasks, there is growing potential for personalized interactions tailored to the subtle and idiosyncratic preferences of the user. We present a public benchmark, PersonalLLM, focusing on adapting LLMs to…

Machine Learning · Computer Science 2025-02-25 Thomas P. Zollo , Andrew Wei Tung Siah , Naimeng Ye , Ang Li , Hongseok Namkoong

As AI systems become increasingly capable and influential, ensuring their alignment with human values, preferences, and goals has become a critical research focus. Current alignment methods primarily focus on designing algorithms and loss…

Computation and Language · Computer Science 2025-05-02 Min-Hsuan Yeh , Jeffrey Wang , Xuefeng Du , Seongheon Park , Leitian Tao , Shawn Im , Yixuan Li

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

Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models (LLMs) due to their reduced computational and memory requirements. This paper investigates the effectiveness of these methods in…

Machine Learning · Computer Science 2024-05-30 Saswat Das , Marco Romanelli , Cuong Tran , Zarreen Reza , Bhavya Kailkhura , Ferdinando Fioretto