Buchumschlag

SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Shi, Qiming, Kang, Zhaolu, Zhou, Yunfan, Weng, Di, Wu, Yingcai
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning
von: Fei, Wu, et al.
Veröffentlicht: (2025)

Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method
von: Lin, Jiayi, et al.
Veröffentlicht: (2024)

Graph Guided Question Answer Generation for Procedural Question-Answering
von: Pham, Hai X., et al.
Veröffentlicht: (2024)

Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering
von: Wen, Wuzhenghong, et al.
Veröffentlicht: (2026)

PeerQA: A Scientific Question Answering Dataset from Peer Reviews
von: Baumgärtner, Tim, et al.
Veröffentlicht: (2025)

A Dataset of Open-Domain Question Answering with Multiple-Span Answers
von: Luo, Zhiyi, et al.
Veröffentlicht: (2024)

General Table Question Answering via Answer-Formula Joint Generation
von: Wang, Zhongyuan, et al.
Veröffentlicht: (2025)

MultiCube-RAG for Multi-hop Question Answering
von: Shi, Jimeng, et al.
Veröffentlicht: (2026)

Question Answering with LLMs and Learning from Answer Sets
von: Borroto, Manuel, et al.
Veröffentlicht: (2025)

LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs
von: Xia, Fei, et al.
Veröffentlicht: (2022)

DPRM: A Dual Implicit Process Reward Model in Multi-Hop Question Answering
von: Wang, Xinyi, et al.
Veröffentlicht: (2025)

I've got the "Answer"! Interpretation of LLMs Hidden States in Question Answering
von: Goloviznina, Valeriya, et al.
Veröffentlicht: (2024)

Intent Aware Context Retrieval for Multi-Turn Agricultural Question Answering
von: Vijayvargia, Abhay, et al.
Veröffentlicht: (2025)

Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering
von: Amirizaniani, Maryam, et al.
Veröffentlicht: (2026)

Multilingual Non-Factoid Question Answering with Answer Paragraph Selection
von: Mishra, Ritwik, et al.
Veröffentlicht: (2024)

Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering
von: Shi, Yucheng, et al.
Veröffentlicht: (2024)

Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questions
von: Liu, Zhe, et al.
Veröffentlicht: (2025)

Optimized Biomedical Question-Answering Services with LLM and Multi-BERT Integration
von: Qian, Cheng, et al.
Veröffentlicht: (2024)

Improving Attributed Long-form Question Answering with Intent Awareness
von: Zhao, Xinran, et al.
Veröffentlicht: (2026)

Exploring Diverse Methods in Visual Question Answering
von: Li, Panfeng, et al.
Veröffentlicht: (2024)

RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs
von: Lin, Can, et al.
Veröffentlicht: (2025)

Uncertainty-Aware Step-wise Verification with Generative Reward Models
von: Ye, Zihuiwen, et al.
Veröffentlicht: (2025)

CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering
von: Huang, Tianyi, et al.
Veröffentlicht: (2026)

A$^2$Search: Ambiguity-Aware Question Answering with Reinforcement Learning
von: Zhang, Fengji, et al.
Veröffentlicht: (2025)

Multi-hop Question Answering
von: Mavi, Vaibhav, et al.
Veröffentlicht: (2022)

From Answers to Questions: EQGBench for Evaluating LLMs' Educational Question Generation
von: Zhou, Chengliang, et al.
Veröffentlicht: (2025)

pdfQA: Diverse, Challenging, and Realistic Question Answering over PDFs
von: Schimanski, Tobias, et al.
Veröffentlicht: (2026)

Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning
von: Beutel, Alex, et al.
Veröffentlicht: (2024)

Uncertainty Estimation of Large Language Models in Medical Question Answering
von: Wu, Jiaxin, et al.
Veröffentlicht: (2024)

Uncertainty-Aware Dynamic Knowledge Graphs for Reliable Question Answering
von: Takahashi, Yu, et al.
Veröffentlicht: (2025)

Knowledge-Aware Diverse Reranking for Cross-Source Question Answering
von: Zhou, Tong
Veröffentlicht: (2025)

NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering
von: Fu, Rong, et al.
Veröffentlicht: (2026)

Comparative Analysis of 47 Context-Based Question Answer Models Across 8 Diverse Datasets
von: Muneeb, Muhammad, et al.
Veröffentlicht: (2025)

Explicit Diversity Conditions for Effective Question Answer Generation with Large Language Models
von: Yadav, Vikas, et al.
Veröffentlicht: (2024)

Multi-hop Question Answering under Temporal Knowledge Editing
von: Cheng, Keyuan, et al.
Veröffentlicht: (2024)

Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
von: Pavlenko, Kirill, et al.
Veröffentlicht: (2026)

Enhancing Large Language Models with Reward-guided Tree Search for Knowledge Graph Question and Answering
von: Long, Xiao, et al.
Veröffentlicht: (2025)

Can We Verify Step by Step for Incorrect Answer Detection?
von: Xu, Xin, et al.
Veröffentlicht: (2024)

DEEPAMBIGQA: Ambiguous Multi-hop Questions for Benchmarking LLM Answer Completeness
von: Ji, Jiabao, et al.
Veröffentlicht: (2025)

Prompt Sensitivity and Answer Consistency of Small Open-Source Language Models for Clinical Question Answering in Low-Resource Healthcare
von: Hariprasad, Shravani
Veröffentlicht: (2026)