mlsanityData to 7 Oct 2026

KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection

arXiv 2310.09044 ↗First posted 13 Oct 2023cs.CL cs.AI cs.LGcited by 43

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable human-level natural language generation capabilities. However, their potential to generate misinformation, often called the hallucination problem, poses a significant risk to their deployment. A common approach to address this issue is to retrieve relevant knowledge and fine-tune the LLM with the knowledge in its input. Unfortunately, this method incurs high training costs and may cause catastrophic forgetting for multi-tasking models. To overcome these limitations, we propose a knowledge-constrained decoding method called KCTS (Knowledge-Constrained Tree Search), which guides a frozen LM to generate text aligned with the reference knowledge at each decoding step using a knowledge classifier score and MCTS (Monte-Carlo Tree Search). To adapt the sequence-level knowledge classifier to token-level guidance, we also propose a novel token-level hallucination detection method called RIPA (Reward Inflection Point Approximation). Our empirical results on knowledge-grounded dialogue and abstractive summarization demonstrate the strength of KCTS as a plug-and-play, model-agnostic decoding method that can effectively reduce hallucinations in natural language generation.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Builds on 67 of its 92 references that are in the map. First posted on arXiv 13 Oct 2023.

Builds on

67 of 92 references.

References · 67

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  7. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  8. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  9. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  10. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  11. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  12. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
38 more
  1. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  2. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  3. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  4. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 888
  5. 2022LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scalecited by 881
  6. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  7. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  8. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  9. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  10. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  11. 2018Object Hallucination in Image Captioningcited by 661
  12. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  13. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
  14. 20218-bit Optimizers via Block-wise Quantizationcited by 395
  15. 2020GeDi: Generative Discriminator Guided Sequence Generationcited by 377
  16. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 376
  17. 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
  18. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  19. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  20. 2023How Language Model Hallucinations Can Snowballcited by 310
  21. 2023Evaluating Verifiability in Generative Search Enginescited by 297
  22. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 291
  23. 2021Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metricscited by 285
  24. 2022Towards a Unified Multi-Dimensional Evaluator for Text Generationcited by 264
  25. 2023Grammar-Constrained Decoding for Structured NLP Tasks without Finetuningcited by 186
  26. 2021The Curious Case of Hallucinations in Neural Machine Translationcited by 161
  27. 2022COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamicscited by 159
  28. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
  29. 2020NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraintscited by 146
  30. 2022Rethinking with Retrieval: Faithful Large Language Model Inferencecited by 145
  31. 2022Training Language Models with Memory Augmentationcited by 112
  32. 2020Entities as Experts: Sparse Memory Access with Entity Supervisioncited by 100
  33. 2020Trading Off Diversity and Quality in Natural Language Generationcited by 94
  34. 2019Learning to Select Knowledge for Response Generation in Dialog Systemscited by 80
  35. 2021Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Featurescited by 74
  36. 2023FELM: Benchmarking Factuality Evaluation of Large Language Modelscited by 66
  37. 2020Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoningcited by 65
  38. 2022Gradient-Based Constrained Sampling from Language Modelscited by 64

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 13; 2025: 23; 2026: 5.

43 papers.

Sort:

By area:

  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  2. 2025s1: Simple test-time scalingcited by 1,311
  3. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Modelscited by 282
  4. 2025Think Only When You Need with Large Hybrid-Reasoning Modelscited by 64
  5. 2025ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templatescited by 62
  6. 2024TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Samplingcited by 61
  7. 2025Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinkingcited by 46
  8. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 45
  9. 2025To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoningcited by 24
  10. 2024Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Modelscited by 23
  11. 2025AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidencecited by 23
  12. 2024SciMMIR: Benchmarking Scientific Multi-modal Information Retrievalcited by 22
31 more
  1. 2025On the Effect of Sampling Diversity in Scaling LLM Inferencecited by 18
  2. 2025CoAT: Chain-of-Associated-Thoughts Framework for Enhancing Large Language Models Reasoningcited by 11
  3. 2024FACTOID: FACtual enTailment fOr hallucInation Detectioncited by 10
  4. 2025On the Query Complexity of Verifier-Assisted Language Generationcited by 10
  5. 2025Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Surveycited by 10
  6. 2025Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generationcited by 10
  7. 2024Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Accesscited by 9
  8. 2025Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Modelscited by 9
  9. 2025CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Modelscited by 9
  10. 2024ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertaintycited by 8
  11. 2025Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detectioncited by 8
  12. 2026UniT: Unified Multimodal Chain-of-Thought Test-time Scalingcited by 8
  13. 2024Groundedness in Retrieval-augmented Long-form Generation: An Empirical Studycited by 7
  14. 2024Fake Artificial Intelligence Generated Contents (FAIGC): A Survey of Theories, Detection Methods, and Opportunitiescited by 7
  15. 2026Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Modelcited by 6
  16. 2025It's Not That Simple. An Analysis of Simple Test-Time Scalingcited by 5
  17. 2023Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decodingcited by 4
  18. 2024CLUE: Concept-Level Uncertainty Estimation for Large Language Modelscited by 4
  19. 2025A*-Decoding: Token-Efficient Inference Scalingcited by 4
  20. 2025Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTScited by 4
  21. 2025Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoningcited by 3
  22. 2024KNOWCOMP POKEMON Team at DialAM-2024: A Two-Stage Pipeline for Detecting Relations in Dialogical Argument Miningcited by 2
  23. 2025PITA: Preference-Guided Inference-Time Alignment for LLM Post-Trainingcited by 2
  24. 2025Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Modelscited by 2
  25. 2025ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Callingcited by 2
  26. 2026CrossHallu: Do Hallucination Signals Generalize Across Languages and Domains in Large Language Model's Internals?cited by 2
  27. 2024A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generationcited by 1
  28. 2024Edit-Constrained Decoding for Sentence Simplificationcited by 1
  29. 2025Breaking the Myth: Can Small Models Infer Postconditions Too?cited by 1
  30. 2026Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decodingcited by 0
  31. 2026Continually self-improving AIcited by 0