Cover Image

Can Hallucinations Be Useful? Solving Multi-Hop Questions With SLMs By Chaining System-I/II Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sengupta, Saptarshi, Wang, Suhang
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions
by: Sengupta, Saptarshi, et al.
Published: (2025)

TOP-Training: Target-Oriented Pretraining for Medical Extractive Question Answering
by: Sengupta, Saptarshi, et al.
Published: (2023)

CCQA: Generating Question from Solution Can Improve Inference-Time Reasoning in SLMs
by: Kim, Jin Young, et al.
Published: (2025)

Exploring Language Model Generalization in Low-Resource Extractive QA
by: Sengupta, Saptarshi, et al.
Published: (2024)

ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers
by: Sengupta, Saptarshi, et al.
Published: (2025)

Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answering
by: Ji, Binquan, et al.
Published: (2025)

StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering
by: Ni, Tengjun, et al.
Published: (2025)

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
by: Wang, Shenzhi, et al.
Published: (2026)

Multi-Hop Reasoning for Question Answering with Hyperbolic Representations
by: Welz, Simon, et al.
Published: (2025)

BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering
by: Zhang, Taolin, et al.
Published: (2025)

Question Calibration and Multi-Hop Modeling for Temporal Question Answering
by: Xue, Chao, et al.
Published: (2024)

$π$-CoT: Prolog-Initialized Chain-of-Thought Prompting for Multi-Hop Question-Answering
by: Wan, Chao, et al.
Published: (2025)

Towards Efficient Methods in Medical Question Answering using Knowledge Graph Embeddings
by: Sengupta, Saptarshi, et al.
Published: (2024)

HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions
by: Shen, Zhiyu, et al.
Published: (2025)

Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents
by: Han, Hojae, et al.
Published: (2026)

Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
by: Shi, Yuling, et al.
Published: (2026)

SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs
by: Alrashed, Sultan
Published: (2024)

Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?
by: Li, Bangzheng, et al.
Published: (2023)

Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA
by: Wu, Yuchen, et al.
Published: (2025)

STOC-TOT: Stochastic Tree-of-Thought with Constrained Decoding for Complex Reasoning in Multi-Hop Question Answering
by: Bi, Zhenyu, et al.
Published: (2024)

Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs
by: Liang, Zhuowen, et al.
Published: (2026)

Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
by: Lu, Yifan, et al.
Published: (2024)

End-to-End Beam Retrieval for Multi-Hop Question Answering
by: Zhang, Jiahao, et al.
Published: (2023)

BioHopR: A Benchmark for Multi-Hop, Multi-Answer Reasoning in Biomedical Domain
by: Kim, Yunsoo, et al.
Published: (2025)

Seek and Solve Reasoning for Table Question Answering
by: Jiang, Ruya, et al.
Published: (2024)

Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering
by: Zhu, Rongzhi, et al.
Published: (2025)

HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation
by: Liu, Hao, et al.
Published: (2025)

DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections
by: Park, Jiwon, et al.
Published: (2025)

NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts
by: Gupta, Abhay, et al.
Published: (2025)

Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning
by: Choi, Minseok, et al.
Published: (2024)

MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering
by: Islamaj, Rezarta, et al.
Published: (2026)

Multi-Hop Question Generation via Dual-Perspective Keyword Guidance
by: Li, Maodong, et al.
Published: (2025)

Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answering
by: Ji, Yuelyu, et al.
Published: (2025)

CRAFT: Calibrated Reasoning with Answer-Faithful Traces via Reinforcement Learning for Multi-Hop Question Answering
by: Liu, Yu, et al.
Published: (2026)

REAP: Enhancing RAG with Recursive Evaluation and Adaptive Planning for Multi-Hop Question Answering
by: Zhu, Yijie, et al.
Published: (2025)

Credible Plan-Driven RAG Method for Multi-Hop Question Answering
by: Zhang, Ningning, et al.
Published: (2025)

ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering
by: Zhu, Yikai, et al.
Published: (2026)

SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering
by: Fu, Yuqing, et al.
Published: (2026)

Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering
by: Lin, Jiuheng, et al.
Published: (2024)

Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs
by: Sen, Jaydip, et al.
Published: (2025)