mlsanityData to 14 Oct 2026

An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering

arXiv 2503.23415 ↗First posted 30 Mar 2025cs.CL cs.AIcited by 2

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Large Language Models (LLMs) frequently produce factually inaccurate outputs - a phenomenon known as hallucination - which limits their accuracy in knowledge-intensive NLP tasks. Retrieval-augmented generation and agentic frameworks such as Reasoning and Acting (ReAct) can address this issue by giving the model access to external knowledge. However, LLMs often fail to remain faithful to retrieved information. Mitigating this is critical, especially if LLMs are required to reason about the retrieved information. Recent research has explored training-free decoding strategies to improve the faithfulness of model generations. We present a systematic analysis of how the combination of the ReAct framework and decoding strategies (i.e., DeCoRe, DoLa, and CAD) can influence the faithfulness of LLM-generated answers. Our results show that combining an agentic framework for knowledge retrieval with decoding methods that enhance faithfulness can increase accuracy on the downstream Multi-Hop Question Answering tasks. For example, we observe an F1 increase from 19.5 to 32.6 on HotpotQA when using ReAct and DoLa.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 25 of its 28 references that are in the map. First posted on arXiv 30 Mar 2025.

Builds on

25 of 28 references.

References · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  7. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  8. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  9. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  11. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  12. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
13 more
  1. 2023DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Modelscited by 376
  2. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
  3. 2023Trusting Your Evidence: Hallucinate Less with Context-aware Decodingcited by 327
  4. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 283
  5. 2024Retrieval Head Mechanistically Explains Long-Context Factualitycited by 232
  6. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretabilitycited by 101
  7. 2024Reducing hallucination in structured outputs via Retrieval-Augmented Generationcited by 93
  8. 2024The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Modelscited by 88
  9. 2024Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Basescited by 77
  10. 2023The Benefits of Bad Advice: Autocontrastive Decoding across Model Layerscited by 29
  11. 2024DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinationscited by 25
  12. 2024The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Modelscited by 17
  13. 2024LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagationcited by 17

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actionscited by 17
  2. 2025Transformers Can Learn Connectivity in Some Graphs but Not Otherscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering
  2. 2025Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems
  3. 2025RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
  4. 2025ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge Graphs
  5. 2025DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router
  6. 2026CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering
  7. 2025BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering
  8. 2026Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model