English
Related papers

Related papers: Human Label Variation as Stable Signal: Learning A…

200 papers

Reinforcement learning from human feedback (RLHF) is widely used to train large language models (LLMs). However, it is unclear whether LLMs accurately learn the underlying preferences in human feedback data. We coin the term \textit{Learned…

Machine Learning · Computer Science 2025-09-22 Luke Marks , Amir Abdullah , Clement Neo , Rauno Arike , David Krueger , Philip Torr , Fazl Barez

Reinforcement Learning, particularly through policy gradient methods, has played a central role in enabling reasoning capabilities of Large Language Models. However, the optimization stability of policy gradients in this setting remains…

Machine Learning · Computer Science 2026-03-03 Luckeciano C. Melo , Alessandro Abate , Yarin Gal

The success of AI assistants based on language models (LLMs) hinges crucially on Reinforcement Learning from Human Feedback (RLHF), which enables the generation of responses more aligned with human preferences. As universal AI assistants,…

Machine Learning · Computer Science 2023-12-27 Rui Zheng , Wei Shen , Yuan Hua , Wenbin Lai , Shihan Dou , Yuhao Zhou , Zhiheng Xi , Xiao Wang , Haoran Huang , Tao Gui , Qi Zhang , Xuanjing Huang

NLP benchmarks rely on standardized datasets for training and evaluating models and are crucial for advancing the field. Traditionally, expert annotations ensure high-quality labels; however, the cost of expert annotation does not scale…

Computation and Language · Computer Science 2025-09-15 Omer Nahum , Nitay Calderon , Orgad Keller , Idan Szpektor , Roi Reichart

Aligning large language models (LLMs) with human values and intents critically involves the use of human or AI feedback. While dense feedback annotations are expensive to acquire and integrate, sparse feedback presents a structural design…

Machine Learning · Computer Science 2024-02-07 Hritik Bansal , John Dang , Aditya Grover

Aligning large language models (LLMs) with human preferences becomes a key component to obtaining state-of-the-art performance, but it yields a huge cost to construct a large human-annotated preference dataset. To tackle this problem, we…

Machine Learning · Computer Science 2025-03-05 Dongyoung Kim , Kimin Lee , Jinwoo Shin , Jaehyung Kim

Reinforcement Learning from Human Feedback (RLHF) is a widely used approach to align large-scale AI systems with human values. However, RLHF typically assumes a single, universal reward, which overlooks diverse preferences and limits…

Machine Learning · Computer Science 2026-03-16 Gihoon Kim , Euntai Kim

Large Language Models (LLMs) have demonstrated remarkable potential in automating software development tasks. While recent advances leverage Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to align models with human…

Software Engineering · Computer Science 2025-12-09 Xin Yin , Chao Ni , Xiaohu Yang

We examine diverging preferences in human-labeled preference datasets. We develop a taxonomy of disagreement sources spanning ten categories across four high-level classes and find that the majority of disagreements are due to factors such…

Computation and Language · Computer Science 2026-03-04 Michael JQ Zhang , Zhilin Wang , Jena D. Hwang , Yi Dong , Olivier Delalleau , Yejin Choi , Eunsol Choi , Xiang Ren , Valentina Pyatkin

While human speakers use a variety of different expressions when describing the same object in an image, giving rise to a distribution of plausible labels driven by pragmatic constraints, the extent to which current Vision & Language Large…

Computation and Language · Computer Science 2024-06-05 Alberto Testoni , Juell Sprott , Sandro Pezzelle

Successfully training a deep neural network demands a huge corpus of labeled data. However, each label only provides limited information to learn from and collecting the requisite number of labels involves massive human effort. In this…

Computation and Language · Computer Science 2020-04-17 Dong-Ho Lee , Rahul Khanna , Bill Yuchen Lin , Jamin Chen , Seyeon Lee , Qinyuan Ye , Elizabeth Boschee , Leonardo Neves , Xiang Ren

Recognizing information disorder is difficult because judgments about manipulation depend on cultural and linguistic context. Yet current Large Language Models (LLMs) often behave as monocultural, English-centric "black boxes," producing…

Computation and Language · Computer Science 2026-03-31 Maziar Kianimoghadam Jouneghani

Multi-label text classification (MLTC) is the task of assigning multiple labels to a given text, and has a wide range of application domains. Most existing approaches require an enormous amount of annotated data to learn a classifier and/or…

Computation and Language · Computer Science 2023-09-26 Muberra Ozmen , Joseph Cotnareanu , Mark Coates

Large Language Models (LLMs) are known to overuse certain terms like "delve" and "intricate." The exact reasons for these lexical choices, however, have been unclear. Using Meta's Llama model, this study investigates the contribution of…

Computation and Language · Computer Science 2025-08-05 Tom S. Juzek , Zina B. Ward

In the context of text classification, the financial burden of annotation exercises for creating training data is a critical issue. Active learning techniques, particularly those rooted in uncertainty sampling, offer a cost-effective…

Computation and Language · Computer Science 2024-06-19 Hamidreza Rouzegar , Masoud Makrehchi

Supervised learning typically focuses on learning transferable representations from training examples annotated by humans. While rich annotations (like soft labels) carry more information than sparse annotations (like hard labels), they are…

In the realm of Natural Language Processing (NLP), common approaches for handling human disagreement consist of aggregating annotators' viewpoints to establish a single ground truth. However, prior studies show that disregarding individual…

Computation and Language · Computer Science 2026-01-13 Benedetta Muscato , Lucia Passaro , Gizem Gezici , Fosca Giannotti

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

Data annotation, the practice of assigning descriptive labels to raw data, is pivotal in optimizing the performance of machine learning models. However, it is a resource-intensive process susceptible to biases introduced by annotators. The…

It is common practice in text classification to only use one majority label for model training even if a dataset has been annotated by multiple annotators. Doing so can remove valuable nuances and diverse perspectives inherent in the…

Computation and Language · Computer Science 2024-09-27 Jin Xu , Mariët Theune , Daniel Braun