mlsanityData to 7 Oct 2026

Faithful Question Answering with Monte-Carlo Planning

arXiv 2305.02556 ↗First posted 4 May 2023cs.CLcited by 16

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Although large language models demonstrate remarkable question-answering performances, revealing the intermediate reasoning steps that the models faithfully follow remains challenging. In this paper, we propose FAME (FAithful question answering with MontE-carlo planning) to answer questions based on faithful reasoning steps. The reasoning steps are organized as a structured entailment tree, which shows how premises are used to produce intermediate conclusions that can prove the correctness of the answer. We formulate the task as a discrete decision-making problem and solve it through the interaction of a reasoning environment and a controller. The environment is modular and contains several basic task-oriented modules, while the controller proposes actions to assemble the modules. Since the search space could be large, we introduce a Monte-Carlo planning algorithm to do a look-ahead search and select actions that will eventually lead to high-quality steps. FAME achieves state-of-the-art performance on the standard benchmark. It can produce valid and faithful reasoning steps compared with large language models with a much smaller model size.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 43 of its 57 references that are in the map. First posted on arXiv 4 May 2023.

Builds on

43 of 57 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees31 Oct
  2. 2022Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner18 May
  3. 2022METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation5 May

Other references · 40

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  7. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  8. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  9. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  10. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  11. 2022Emergent Abilities of Large Language Modelscited by 2,483
  12. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
28 more
  1. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  2. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  3. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  4. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  5. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  6. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  7. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
  8. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  9. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  10. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  11. 2022Can language models learn from explanations in context?cited by 248
  12. 2021Explaining Answers with Entailment Treescited by 148
  13. 2022Faithful Reasoning Using Large Language Modelscited by 130
  14. 2021Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processingcited by 126
  15. 2022Teaching Algorithmic Reasoning via In-context Learningcited by 111
  16. 2022LAMBADA: Backward Chaining for Automated Reasoning in Natural Languagecited by 66
  17. 2020QED: A Framework and Dataset for Explanations in Question Answeringcited by 55
  18. 2021Machine Translation Decoding beyond Beam Searchcited by 55
  19. 2022Generating Natural Language Proofs with Verifier-Guided Searchcited by 52
  20. 2021General-Purpose Question-Answering with Macawcited by 40
  21. 2022Entailer: Answering Questions with Faithful and Truthful Chains of Reasoningcited by 38
  22. 2022Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvementcited by 37
  23. 2022Natural Language Deduction through Search over Statement Compositionscited by 35
  24. 2020A Survey on Explainability in Machine Reading Comprehensioncited by 33
  25. 2021PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decodingcited by 32
  26. 2022FaiRR: Faithful and Robust Deductive Reasoning over Natural Languagecited by 29
  27. 2021Do Answers to Boolean Questions Need Explanations? Yescited by 5
  28. 2022MetaLogic: Logical Reasoning Explanations with Fine-Grained Structurecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 7; 2025: 5; 2026: 2.

16 papers.

Sort:

By area:

  1. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  2. 2024Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMscited by 224
  3. 2024WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Explorationcited by 100
  4. 2024FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answeringcited by 38
  5. 2024Multi-hop Question Answering under Temporal Knowledge Editingcited by 36
  6. 2025Thinking Machines: A Survey of LLM based Reasoning Strategiescited by 25
  7. 2024UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Constructioncited by 15
  8. 2024Leveraging Logical Rules in Knowledge Editing: A Cherry on the Topcited by 11
  9. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphscited by 8
  10. 2024SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learningcited by 3
  11. 2023Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answeringcited by 2
  12. 2025SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Contextcited by 1
4 more
  1. 2025Follow My Lead: Logical Fallacy Classification with Knowledge-Augmented LLMscited by 1
  2. 2025Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generationcited by 0
  3. 2026GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Trackingcited by 0
  4. 2026EviGraph: Proof-Carrying Selective Recommendation over Temporal Public-Service Knowledge Graphscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MCTS-KBQA: Monte Carlo Tree Search with Information Gain Rewards for Knowledge Base Question Answering
  2. 2024Refining Answer Distributions for Improved Large Language Model Reasoning
  3. 2023Question Decomposition Improves the Faithfulness of Model-Generated Reasoning
  4. 2026Distilling Reasoning Without Knowledge: A Framework for Reliable LLMs
  5. 2024Zero-Shot Multi-Hop Question Answering via Monte-Carlo Tree Search with Large Language Models
  6. 2023Probing the Multi-turn Planning Capabilities of LLMs via 20 Question Games
  7. 2024Seek and Solve Reasoning for Table Question Answering
  8. 2026Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS