English
Related papers

Related papers: Diverging Preferences: When do Annotators Disagree…

200 papers

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…

Computation and Language · Computer Science 2026-01-21 Zixuan Liu , Siavash H. Khajavi , Guangkai Jiang , Xinru Liu

Large language models (LLMs) have shown impressive achievements in solving a broad range of tasks. Augmented by instruction fine-tuning, LLMs have also been shown to generalize in zero-shot settings as well. However, whether LLMs closely…

Computation and Language · Computer Science 2023-10-30 Noah Lee , Na Min An , James Thorne

People naturally vary in their annotations for subjective questions and some of this variation is thought to be due to the person's sociodemographic characteristics. LLMs have also been used to label data, but recent work has shown that…

Computation and Language · Computer Science 2025-03-03 Matthias Orlikowski , Jiaxin Pei , Paul Röttger , Philipp Cimiano , David Jurgens , Dirk Hovy

Hate speech spreads widely online, harming individuals and communities, making automatic detection essential for large-scale moderation, yet detecting it remains difficult. Part of the challenge lies in subjectivity: what one person flags…

Computation and Language · Computer Science 2025-12-11 Paloma Piot , David Otero , Patricia Martín-Rodilla , Javier Parapar

Subjective NLP tasks usually rely on human annotations provided by multiple annotators, whose judgments may vary due to their diverse backgrounds and life experiences. Traditional methods often aggregate multiple annotations into a single…

Computation and Language · Computer Science 2025-10-17 Benedetta Muscato , Praveen Bushipaka , Gizem Gezici , Lucia Passaro , Fosca Giannotti

We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of…

Machine Learning · Statistics 2025-12-04 Pangpang Liu , Junwei Lu , Will Wei Sun

While Reinforcement Learning from Human Feedback (RLHF) is widely used to align Large Language Models (LLMs) with human preferences, it typically assumes homogeneous preferences across users, overlooking diverse human values and minority…

Computation and Language · Computer Science 2025-10-28 Yijiang River Dong , Tiancheng Hu , Yinhong Liu , Ahmet Üstün , Nigel Collier

Incorporating every annotator's perspective is crucial for unbiased data modeling. Annotator fatigue and changing opinions over time can distort dataset annotations. To combat this, we propose to learn a more accurate representation of…

Machine Learning · Computer Science 2024-06-05 Uthman Jinadu , Yi Ding

Large language models (LLMs) offer strategy researchers powerful tools for annotating text at scale, but treating LLM-generated labels as deterministic overlooks substantial instability. Grounded in content analysis and generalizability…

Computers and Society · Computer Science 2026-01-21 Arnaldo Camuffo , Alfonso Gambardella , Saeid Kazemi , Jakub Malachowski , Abhinav Pandey

Human variation in labeling is often considered noise. Annotation projects for machine learning (ML) aim at minimizing human label variation, with the assumption to maximize data quality and in turn optimize and maximize machine learning…

Computation and Language · Computer Science 2022-11-07 Barbara Plank

Supervised machine learning often requires human-annotated data. While annotator disagreement is typically interpreted as evidence of noise, population-level label distribution learning (PLDL) treats the collection of annotations for each…

Machine Learning · Computer Science 2021-06-22 Tharindu Cyril Weerasooriya , Tong Liu , Christopher M. Homan

As large language models (LLMs) advance their capabilities, aligning these models with human preferences has become crucial. Preference optimization, which trains models to distinguish between preferred and non-preferred responses based on…

Machine Learning · Computer Science 2026-02-02 Shawn Im , Sharon Li

In the absence of abundant reliable annotations for challenging tasks and contexts, how can we expand the frontier of LLM capabilities with potentially wrong answers? We focus on two research questions: (1) Can LLMs generate reliable…

Computation and Language · Computer Science 2024-10-16 Jihan Yao , Wenxuan Ding , Shangbin Feng , Lucy Lu Wang , Yulia Tsvetkov

In many applications, human and LLM evaluators use assessments of relevant criteria to create an overall evaluation for an item or individual. For example, in admissions, committees assess candidates on attributes such as test scores, GPA,…

Machine Learning · Computer Science 2026-05-19 Madeline Celi Kitch , Nihar B. Shah

Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for…

As various post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to develop a deeper understanding of whether and when the explanations output by these methods…

Machine Learning · Computer Science 2025-04-18 Satyapriya Krishna , Tessa Han , Alex Gu , Steven Wu , Shahin Jabbari , Himabindu Lakkaraju

Learning analytics researchers often analyze qualitative student data such as coded annotations or interview transcripts to understand learning processes. With the rise of generative AI, fully automated and human-AI workflows have emerged…

Computation and Language · Computer Science 2026-01-21 Elham Tajik , Conrad Borchers , Bahar Shahrokhian , Sebastian Simon , Ali Keramati , Sonika Pal , Sreecharan Sankaranarayanan

Human label variation arises when annotators assign different labels to the same item for valid reasons, while annotation errors occur when labels are assigned for invalid reasons. These two issues are prevalent in NLP benchmarks, yet…

Computation and Language · Computer Science 2024-06-07 Leon Weber-Genzel , Siyao Peng , Marie-Catherine de Marneffe , Barbara Plank

Despite the significant progress made by existing retrieval augmented language models (RALMs) in providing trustworthy responses and grounding in reliable sources, they often overlook effective alignment with human preferences. In the…

Computation and Language · Computer Science 2024-12-19 Zhuoran Jin , Hongbang Yuan , Tianyi Men , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

Human label variation (Plank 2022), or annotation disagreement, exists in many natural language processing (NLP) tasks. To be robust and trusted, NLP models need to identify such variation and be able to explain it. To this end, we created…

Computation and Language · Computer Science 2023-04-26 Nan-Jiang Jiang , Chenhao Tan , Marie-Catherine de Marneffe