Cover Image

LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Long, Do Xuan, Ngoc, Hai Nguyen, Sim, Tiviatis, Dao, Hieu, Joty, Shafiq, Kawaguchi, Kenji, Chen, Nancy F., Kan, Min-Yen
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

What Makes a Good Natural Language Prompt?
by: Long, Do Xuan, et al.
Published: (2025)

Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines
by: Long, Do Xuan, et al.
Published: (2025)

Aligning Large Language Models with Human Opinions through Persona Selection and Value--Belief--Norm Reasoning
by: Long, Do Xuan, et al.
Published: (2023)

Who's important? -- SUnSET: Synergistic Understanding of Stakeholder, Events and Time for Timeline Generation
by: Sim, Tiviatis, et al.
Published: (2025)

StructTest: Benchmarking LLMs' Reasoning through Compositional Structured Outputs
by: Chen, Hailin, et al.
Published: (2024)

Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models
by: Long, Do Xuan, et al.
Published: (2024)

Demystifying Domain-adaptive Post-training for Financial LLMs
by: Ke, Zixuan, et al.
Published: (2025)

Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts
by: Nguyen, Xuan-Phi, et al.
Published: (2023)

Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models
by: Zhang, Yang, et al.
Published: (2024)

Output Format Biases in the Evaluation of Large Language Models for Code Translation
by: Macedo, Marcos, et al.
Published: (2024)

Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction
by: Shi, Zhenmei, et al.
Published: (2024)

Exploiting LLMs' Reasoning Capability to Infer Implicit Concepts in Legal Information Retrieval
by: Nguyen, Hai-Long, et al.
Published: (2024)

DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation
by: Li, Minzhi, et al.
Published: (2024)

Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning
by: Qin, Chengwei, et al.
Published: (2023)

Explainable Fraud Detection with GNNExplainer and Shapley Values
by: Dao, Ngoc Hieu
Published: (2025)

Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs
by: Matsuda, Hiroshi, et al.
Published: (2025)

Are LLMs Ready for TOON? Benchmarking Structural Correctness-Sustainability Trade-offs in Novel Structured Output Formats
by: Masciari, Elio, et al.
Published: (2026)

Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization
by: Li, Chuyuan, et al.
Published: (2025)

Reasoning Robustness of LLMs to Adversarial Typographical Errors
by: Gan, Esther, et al.
Published: (2024)

Personalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation
by: Chen, Hailin, et al.
Published: (2023)

Unsupervised Summarization Re-ranking
by: Ravaut, Mathieu, et al.
Published: (2022)

Assessing Gender Bias in LLMs: Comparing LLM Outputs with Human Perceptions and Official Statistics
by: Bas, Tetiana
Published: (2024)

ParaICL: Towards Parallel In-Context Learning
by: Li, Xingxuan, et al.
Published: (2024)

FMBench: Adaptive Large Language Model Output Formatting
by: Wang, Yaoting, et al.
Published: (2026)

Decoupling Task-Solving and Output Formatting in LLM Generation
by: Deng, Haikang, et al.
Published: (2025)

On Positional Bias of Faithfulness for Long-form Summarization
by: Wan, David, et al.
Published: (2024)

"Global is Good, Local is Bad?": Understanding Brand Bias in LLMs
by: Kamruzzaman, Mahammed, et al.
Published: (2024)

SFR-RAG: Towards Contextually Faithful LLMs
by: Nguyen, Xuan-Phi, et al.
Published: (2024)

StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs
by: Yang, Jialin, et al.
Published: (2025)

How Good Are LLMs at Processing Tool Outputs?
by: Kate, Kiran, et al.
Published: (2025)

From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text
by: Mahbub, Ridwan, et al.
Published: (2025)

Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis
by: Raj, Chahat, et al.
Published: (2024)

Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data
by: Liu, Jiacheng, et al.
Published: (2025)

LLMs are Biased Evaluators But Not Biased for Retrieval Augmented Generation
by: Chen, Yen-Shan, et al.
Published: (2024)

A$^2$RD: Agentic Autoregressive Diffusion for Long Video Consistency
by: Long, Do Xuan, et al.
Published: (2026)

Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows
by: Ming, Yifei, et al.
Published: (2025)

J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization
by: Xu, Austin, et al.
Published: (2025)

Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts
by: Nguyen, Xuan-Phi, et al.
Published: (2026)

Structured Outputs Enable General-Purpose LLMs to be Medical Experts
by: Guo, Guangfu, et al.
Published: (2025)

SO-Bench: A Structural Output Evaluation of Multimodal LLMs
by: Feng, Di, et al.
Published: (2025)