mlsanityData to 14 Oct 2026

Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension

arXiv 2306.12069 ↗First posted 21 Jun 2023cs.CL cs.LGcited by 1

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

Abstract (arXiv)

Machine reading comprehension (MRC) poses new challenges over logical reasoning, which aims to understand the implicit logical relations entailed in the given contexts and perform inference over them. Due to the complexity of logic, logical relations exist at different granularity levels. However, most existing methods of logical reasoning individually focus on either entity-aware or discourse-based information but ignore the hierarchical relations that may even have mutual effects. In this paper, we propose a holistic graph network (HGN) which deals with context at both discourse level and word level, as the basis for logical reasoning, to provide a more fine-grained relation extraction. Specifically, node-level and type-level relations, which can be interpreted as bridges in the reasoning process, are modeled by a hierarchical interaction mechanism to improve the interpretation of MRC systems. Experimental results on logical reasoning QA datasets (ReClor and LogiQA) and natural language inference datasets (SNLI and ANLI) show the effectiveness and generalization of our method, and in-depth analysis verifies its capability to understand complex logical relations.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 32 of its 40 references that are in the map. First posted on arXiv 21 Jun 2023.

Builds on

32 of 40 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  5. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  6. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  7. 2015Teaching Machines to Read and Comprehendcited by 1,049
  8. 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 861
  9. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 807
  10. 2018CoQA: A Conversational Question Answering Challengecited by 683
  11. 2018QuAC : Question Answering in Contextcited by 381
  12. 2019Abductive Commonsense Reasoningcited by 301
20 more
  1. 2019Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoningcited by 285
  2. 2020ReClor: A Reading Comprehension Dataset Requiring Logical Reasoningcited by 217
  3. 2020Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learningcited by 216
  4. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 196
  5. 2020Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphscited by 129
  6. 2020MuTual: A Dataset for Multi-Turn Dialogue Reasoningcited by 115
  7. 2020Adversarial Training for Large Neural Language Modelscited by 111
  8. 2020InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspectivecited by 92
  9. 2020Retrospective Reader for Machine Reading Comprehensioncited by 86
  10. 2019Hierarchical Graph Network for Multi-hop Question Answeringcited by 83
  11. 2019Cognitive Graph for Multi-Hop Reading Comprehension at Scalecited by 65
  12. 2019Dynamically Fused Graph Network for Multi-hop Reasoningcited by 63
  13. 2019SG-Net: Syntax-Guided Machine Reading Comprehensioncited by 52
  14. 2021AR-LSAT: Investigating Analytical Reasoning of Textcited by 51
  15. 2021Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Textcited by 46
  16. 2019Multi-hop Question Answering via Reasoning Chainscited by 42
  17. 2020Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Readingcited by 33
  18. 2021DAGN: Discourse-Aware Graph Network for Logical Reasoningcited by 28
  19. 2020Dialogue Graph Modeling for Conversational Machine Readingcited by 26
  20. 2020Machine Reading Comprehension: The Role of Contextualized Language Models and Beyondcited by 21

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Dr.Academy: A Benchmark for Evaluating Questioning Capability in Education for Large Language Modelscited by 6

Similar, not cited

Close in wording, no citation either way

  1. 2022Discourse-Aware Graph Networks for Textual Logical Reasoning
  2. 2022Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning
  3. 2022AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension
  4. 2025Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning
  5. 2024Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge Utilization
  6. 2025Grounding LLM Reasoning with Knowledge Graphs
  7. 2026H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models
  8. 2023Evaluating the Rationale Understanding of Critical Reasoning in Logical Reading Comprehension