English
Related papers

Related papers: Diverging Preferences: When do Annotators Disagree…

200 papers

Large language models (LLMs) have demonstrated significant capability to generalize across a large number of NLP tasks. For industry applications, it is imperative to assess the performance of the LLM on unlabeled production data from time…

Computation and Language · Computer Science 2023-11-21 Wei Du , Laksh Advani , Yashmeet Gambhir , Daniel J Perry , Prashant Shiralkar , Zhengzheng Xing , Aaron Colak

Learning human preferences in language models remains fundamentally challenging, as reward modeling relies on subtle, subjective comparisons or shades of gray rather than clear-cut labels. This study investigates the limits of current…

Computation and Language · Computer Science 2026-04-03 Simona-Vasilica Oprea , Adela Bâra

Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, reward modeling based on the Bradley-Terry (BT) model assumes a…

Artificial Intelligence · Computer Science 2025-09-24 Jingyan Shen , Jiarui Yao , Rui Yang , Yifan Sun , Feng Luo , Rui Pan , Tong Zhang , Han Zhao

Solving complex classification tasks using deep neural networks typically requires large amounts of annotated data. However, corresponding class labels are noisy when provided by error-prone annotators, e.g., crowdworkers. Training standard…

Machine Learning · Computer Science 2023-10-25 Marek Herde , Denis Huseljic , Bernhard Sick

A common practice in building NLP datasets, especially using crowd-sourced annotations, involves obtaining multiple annotator judgements on the same data instances, which are then flattened to produce a single "ground truth" label or score,…

Computation and Language · Computer Science 2021-10-13 Vinodkumar Prabhakaran , Aida Mostafazadeh Davani , Mark Díaz

Large language models are increasingly used to annotate texts, but their outputs reflect some human perspectives better than others. Existing methods for correcting LLM annotation error assume a single ground truth. However, this assumption…

Computation and Language · Computer Science 2026-03-24 Navya Mehrotra , Adam Visokay , Kristina Gligorić

Large Language Models (LLMs) annotated datasets are widely used nowadays, however, large-scale annotations often show biases in low-quality datasets. For example, Multiple-Choice Questions (MCQs) datasets with one single correct option is…

Computation and Language · Computer Science 2026-01-08 Zipeng Ling , Shuliang Liu , Yuehao Tang , Chen Huang , Gaoyang Jiang , Shenghong Fu , Junqi Yang , Yao Wan , Jiawan Zhang , Kejia Huang , Xuming Hu

Preference mechanisms, such as human preference, LLM-as-a-Judge (LaaJ), and reward models, are central to aligning and evaluating large language models (LLMs). Yet, the underlying concepts that drive these preferences remain poorly…

Computation and Language · Computer Science 2025-05-30 Nitay Calderon , Liat Ein-Dor , Roi Reichart

When annotators disagree on a label, the disagreement itself carries signal -- and the number of annotators needed to capture it depends on the evaluation metric. We fine-tune NLI models on label distributions subsampled from ChaosNLI, a…

Computation and Language · Computer Science 2026-05-29 Guneet Kohli

As NLP models become increasingly integrated into real-world applications, it becomes clear that there is a need to address the fact that models often rely on and generate conflicting information. Conflicts could reflect the complexity of…

Computation and Language · Computer Science 2026-02-03 Siyi Liu , Dan Roth

This paper investigates the automation of qualitative data analysis, focusing on inductive coding using large language models (LLMs). Unlike traditional approaches that rely on deductive methods with predefined labels, this research…

Computation and Language · Computer Science 2025-12-02 Angelina Parfenova , Andreas Marfurt , Alexander Denzler , Juergen Pfeffer

Large language models (LLMs) are increasingly positioned as scalable tools for annotating educational data, including classroom discourse, interaction logs, and qualitative learning artifacts. Their ability to rapidly summarize…

Artificial Intelligence · Computer Science 2026-03-17 Bakhtawar Ahtisham , Kirk Vanacore , Rene F. Kizilcec

Performance of Large Language Models (LLMs) on multiple-choice tasks differs markedly between symbol-based and cloze-style evaluation formats. The observed discrepancies are systematically attributable to task characteristics: natural…

Computation and Language · Computer Science 2026-02-02 Joonhak Lee , Sungmok Jung , Jongyeon Park , Jaejin Lee

The emergence of powerful LLMs has led to a paradigm shift in Natural Language Understanding and Natural Language Generation. The properties that make LLMs so valuable for these tasks -- creativity, ability to produce fluent speech, and…

Computation and Language · Computer Science 2025-03-10 Kelsey Kraus , Margaret Kroll

What if large language models could not only infer human mindsets but also expose every blind spot in team dialogue such as discrepancies in the team members' joint understanding? We present a novel, two-step framework that leverages large…

Computation and Language · Computer Science 2025-09-03 Katharine Kowalyshyn , Matthias Scheutz

Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference pipeline. In a human choice blindness study, 91% of…

Computation and Language · Computer Science 2026-03-10 Wenbin Wu

Large language models (LLMs) increasingly operate as autonomous agents that reason over external APIs to perform complex tasks. However, their reliability and agreement remain poorly characterized. We present a unified benchmarking…

Information Retrieval · Computer Science 2026-04-28 Eyhab Al-Masri

Span annotation - annotating specific text features at the span level - can be used to evaluate texts where single-score metrics fail to provide actionable feedback. Until recently, span annotation was done by human annotators or fine-tuned…

The increasing use of LLMs as substitutes for humans in ``aligning'' LLMs has raised questions about their ability to replicate human judgments and preferences, especially in ambivalent scenarios where humans disagree. This study examines…

Computation and Language · Computer Science 2025-06-02 Bhaktipriya Radharapu , Manon Revel , Megan Ung , Sebastian Ruder , Adina Williams

Disagreements are common in online discussions. Disagreement may foster collaboration and improve the quality of a discussion under some conditions. Although there exist methods for recognizing disagreement, a deeper understanding of…

Computation and Language · Computer Science 2024-10-03 Michiel van der Meer , Piek Vossen , Catholijn M. Jonker , Pradeep K. Murukannaiah