Image de couverture de livre

Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yao, Jui-Ming, Chen, Hao-Yuan, Tang, Zi-Xian, Tan, Bing-Jia, Peng, Sheng-Wei, Xie, Bing-Cheng, Su, Shun-Feng
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Multi-TW: Benchmarking Multimodal Models on Traditional Chinese Question Answering in Taiwan
par: Yao, Jui-Ming, et autres
Publié: (2025)

Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering
par: Hu, Zhongjian, et autres
Publié: (2024)

Rationale-guided Prompting for Knowledge-based Visual Question Answering
par: Hu, Zhongjian, et autres
Publié: (2024)

Unlocking Temporal Question Answering for Large Language Models with Tailor-Made Reasoning Logic
par: Li, Xingxuan, et autres
Publié: (2023)

Compositional Consistency-Guided Decoding for Three-Way Logical Question Answering
par: Huang, Tianyi, et autres
Publié: (2026)

Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering
par: Chu, Zheng, et autres
Publié: (2025)

Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering
par: Liu, Runxuan, et autres
Publié: (2025)

MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering
par: Ness, Robert Osazuwa, et autres
Publié: (2024)

Improved LLM Agents for Financial Document Question Answering
par: Tan, Nelvin, et autres
Publié: (2025)

Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning
par: Chen, Ming, et autres
Publié: (2025)

DMC$^3$: Dual-Modal Counterfactual Contrastive Construction for Egocentric Video Question Answering
par: Zou, Jiayi, et autres
Publié: (2025)

A Benchmark for Long-Form Medical Question Answering
par: Hosseini, Pedram, et autres
Publié: (2024)

Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling
par: Cappelletti, Silvia, et autres
Publié: (2025)

SeGPruner: Semantic-Geometric Visual Token Pruner for 3D Question Answering
par: Li, Wenli, et autres
Publié: (2026)

New Constraints on Cosmic-ray boosted Sub-GeV Dark Matter via Light Mediators
par: Yu, Yang, et autres
Publié: (2025)

MetaRA: Metamorphic Robustness Assessment for Multimodal Large Language Model-based Visual Question Answering Systems
par: Xu, Quanxing, et autres
Publié: (2026)

Biomedical Question Answering: A Survey of Approaches and Challenges
par: Jin, Qiao, et autres
Publié: (2021)

CLEAR-KGQA: Clarification-Enhanced Ambiguity Resolution for Knowledge Graph Question Answering
par: Wen, Liqiang, et autres
Publié: (2025)

Holographic Entanglement Entropy for Brane-World Higher Derivative Gravity
par: Miao, Rong-Xin, et autres
Publié: (2024)

Improving Data Augmentation for Robust Visual Question Answering with Effective Curriculum Learning
par: Zheng, Yuhang, et autres
Publié: (2024)

Neutral test particle dynamics around the Bardeen-AdS black hole surrounded by quintessence dark energy
par: Xie, Jiayu, et autres
Publié: (2024)

Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models
par: Wu, Jialiang, et autres
Publié: (2025)

Ontology-Aware RAG for Improved Question-Answering in Cybersecurity Education
par: Zhao, Chengshuai, et autres
Publié: (2024)

CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering
par: Yang, Hao, et autres
Publié: (2026)

ChineseVideoBench: Benchmarking Multi-modal Large Models for Chinese Video Question Answering
par: Nie, Yuxiang, et autres
Publié: (2025)

CE-GOCD: Central Entity-Guided Graph Optimization for Community Detection to Augment LLM Scientific Question Answering
par: Lan, Jiayin, et autres
Publié: (2026)

Improving Semantic Uncertainty Quantification in Language Model Question-Answering via Token-Level Temperature Scaling
par: Lamb, Tom A., et autres
Publié: (2026)

LIVE: Learnable In-Context Vector for Visual Question Answering
par: Peng, Yingzhe, et autres
Publié: (2024)

First Token Probability Guided RAG for Telecom Question Answering
par: Chen, Tingwei, et autres
Publié: (2025)

Wasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering
par: Hagen, Luca, et autres
Publié: (2026)

A new paradigm for cancer immunotherapy: Orchestrating type 1 and type 2 immunity for curative response
par: Bing Feng, et autres
Publié: (2024)

Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts
par: Chen, Zhuo, et autres
Publié: (2024)

Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning
par: Tan, Qingyu, et autres
Publié: (2023)

Dynamical origin of universal two-pole structures and their light quark mass evolution
par: Xie, Jia-Ming, et autres
Publié: (2023)

Two-pole structures in QCD -- a universal phenomenon governed by chiral dynamics
par: Xie, Jia-Ming, et autres
Publié: (2025)

Verbal Process Supervision Elicits Better Coding Agents
par: Chen, Hao-Yuan, et autres
Publié: (2025)

BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering
par: Chu, Zheng, et autres
Publié: (2024)

A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions
par: Inadumi, Shun, et autres
Publié: (2024)

RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
par: Yuan, Bo, et autres
Publié: (2026)

Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering
par: Hu, Yinghao, et autres
Publié: (2025)