Cover Image

BoN Appetit Team at LeWiDi-2025: Best-of-N Test-time Scaling Can Not Stomach Annotation Disagreements (Yet)

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ruiz, Tomas, Peng, Siyao, Plank, Barbara, Schwemmer, Carsten
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LeWiDi-2025 at NLPerspectives: Third Edition of the Learning with Disagreements Shared Task
by: Leonardelli, Elisa, et al.
Published: (2025)

DeMeVa at LeWiDi-2025: Modeling Perspectives with In-Context Learning and Label Distribution Learning
by: Ignatev, Daniil, et al.
Published: (2025)

LPI-RIT at LeWiDi-2025: Improving Distributional Predictions via Metadata and Loss Reweighting with DisCo
by: Sawkar, Mandira, et al.
Published: (2025)

Opt-ICL at LeWiDi-2025: Maximizing In-Context Signal from Rater Examples via Meta-Learning
by: Sorensen, Taylor, et al.
Published: (2025)

MaiBaam Annotation Guidelines
by: Blaschke, Verena, et al.
Published: (2024)

CarBoN: Calibrated Best-of-N Sampling Improves Test-time Reasoning
by: Tang, Yung-Chen, et al.
Published: (2025)

RoBoN: Routed Online Best-of-n for Test-Time Scaling with Multiple LLMs
by: Geuter, Jonathan, et al.
Published: (2025)

AdaBoN: Adaptive Best-of-N Alignment
by: Raman, Vinod, et al.
Published: (2025)

Different Tastes of Entities: Investigating Human Label Variation in Named Entity Annotations
by: Peng, Siyao, et al.
Published: (2024)

Rethinking Ground Truth: A Case Study on Human Label Variation in MLLM Benchmarking
by: Ruiz, Tomas, et al.
Published: (2026)

EEVEE: An Easy Annotation Tool for Natural Language Processing
by: Sorensen, Axel, et al.
Published: (2024)

VariErr NLI: Separating Annotation Error from Human Label Variation
by: Weber-Genzel, Leon, et al.
Published: (2024)

CLIMATELI: Evaluating Entity Linking on Climate Change Data
by: Zhou, Shijia, et al.
Published: (2024)

EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI
by: Zuo, Longfei, et al.
Published: (2025)

Mind the Uncertainty in Human Disagreement: Evaluating Discrepancies between Model Predictions and Human Responses in VQA
by: Lan, Jian, et al.
Published: (2024)

TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
by: Qiu, Jiahao, et al.
Published: (2024)

Team Disagreement and Productive Persuasion
by: Bonomi, Giampaolo
Published: (2025)

BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
by: Gui, Lin, et al.
Published: (2024)

JuniperLiu at CoMeDi Shared Task: Models as Annotators in Lexical Semantics Disagreements
by: Liu, Zhu, et al.
Published: (2024)

Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?
by: Khurana, Urja, et al.
Published: (2024)

Donkii: Can Annotation Error Detection Methods Find Errors in Instruction-Tuning Datasets?
by: Weber-Genzel, Leon, et al.
Published: (2023)

"Seeing the Big through the Small": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?
by: Chen, Beiduo, et al.
Published: (2024)

MultiClimate: Multimodal Stance Detection on Climate Change Videos
by: Wang, Jiawen, et al.
Published: (2024)

A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI
by: Chen, Beiduo, et al.
Published: (2024)

Funzac at CoMeDi Shared Task: Modeling Annotator Disagreement from Word-In-Context Perspectives
by: Sarumi, Olufunke O., et al.
Published: (2025)

MaiBaam: A Multi-Dialectal Bavarian Universal Dependency Treebank
by: Blaschke, Verena, et al.
Published: (2024)

Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?
by: Ni, Jingwei, et al.
Published: (2025)

Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification
by: Xu, Shanshan, et al.
Published: (2024)

From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification
by: Xu, Shanshan, et al.
Published: (2023)

The Best is Yet to Come: Graph Convolution in the Testing Phase for Multimodal Recommendation
by: Xu, Jinfeng, et al.
Published: (2025)

Leveraging Annotator Disagreement for Text Classification
by: Xu, Jin, et al.
Published: (2024)

Information Asymmetry across Language Varieties: A Case Study on Cantonese-Mandarin and Bavarian-German QA
by: Pei, Renhao, et al.
Published: (2026)

Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding
by: Wang, Yiming, et al.
Published: (2025)

MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs
by: Zhao, Raoyuan, et al.
Published: (2025)

Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
by: Huang, Audrey, et al.
Published: (2025)

Calibrating Probabilistic Object Detectors with Annotator Disagreement
by: Tan, Zhi Qin, et al.
Published: (2026)

Dealing with Annotator Disagreement in Hate Speech Classification
by: Dehghan, Somaiyeh, et al.
Published: (2025)

DiZiNER: Disagreement-guided Instruction Refinement via Pilot Annotation Simulation for Zero-shot Named Entity Recognition
by: Kim, Siun, et al.
Published: (2026)

Hitchcock's Appetites
by: McKittrick, Casey
Published: (2016)

Display Week 2026 Promises to be the Best Yet
by: Ioannis (John) Kymissis
Published: (2026)