mlsanityData to 14 Oct 2026

Learning a Structural Causal Model for Intuition Reasoning in Conversation

arXiv 2305.17727 ↗First posted 28 May 2023cs.CLcited by 7

On the map: LLM reasoning → Causal reasoning in LLMs

Abstract (arXiv)

Reasoning, a crucial aspect of NLP research, has not been adequately addressed by prevailing models including Large Language Model. Conversation reasoning, as a critical component of it, remains largely unexplored due to the absence of a well-designed cognitive model. In this paper, inspired by intuition theory on conversation cognition, we develop a conversation cognitive model (CCM) that explains how each utterance receives and activates channels of information recursively. Besides, we algebraically transformed CCM into a structural causal model (SCM) under some mild assumptions, rendering it compatible with various causal discovery methods. We further propose a probabilistic implementation of the SCM for utterance-level relation reasoning. By leveraging variational inference, it explores substitutes for implicit causes, addresses the issue of their unobservability, and reconstructs the causal representations of utterances through the evidence lower bounds. Moreover, we constructed synthetic and simulated datasets incorporating implicit causes and complete cause labels, alleviating the current situation where all available datasets are implicit-causes-agnostic. Extensive experiments demonstrate that our proposed method significantly outperforms existing methods on synthetic, simulated, and real-world datasets. Finally, we analyze the performance of CCM under latent confounders and propose theoretical ideas for addressing this currently unresolved issue.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning. Builds on 6 of its 99 references that are in the map. First posted on arXiv 28 May 2023.

Builds on

6 of 99 references.

References · 6

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  2. 2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 233
  3. 2022Rationale-Augmented Ensembles in Language Modelscited by 111
  4. 2023Dissociating language and thought in large language modelscited by 29
  5. 2021The DeCAMFounder: Non-Linear Causal Discovery in the Presence of Hidden Variablescited by 15
  6. 2022Non-Axiomatic Term Logic: A Computational Theory of Cognitive Symbolic Reasoningcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 5.

7 papers.

  1. 2024Revisiting Multimodal Emotion Recognition in Conversation from the Perspective of Graph Spectrumcited by 33
  2. 2024Large Language Models and Causal Inference in Collaboration: A Surveycited by 26
  3. 2024A Causal Explainable Guardrails for Large Language Modelscited by 18
  4. 2024The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trendscited by 11
  5. 2023SSL Framework for Causal Inconsistency between Structures and Representationscited by 2
  6. 2023A Review and Roadmap of Deep Causal Model from Different Causal Structures and Representationscited by 1
  7. 2024Towards Causal Relationship in Indefinite Data: Baseline Model and New Datasetscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023How to Enhance Causal Discrimination of Utterances: A Case on Affective Reasoning
  2. 2026NoisyCausal: A Benchmark for Evaluating Causal Reasoning Under Structured Noise
  3. 2023CLadder: Assessing Causal Reasoning in Language Models
  4. 2025Enabling Conversational Behavior Reasoning Capabilities in Full-Duplex Speech
  5. 2025CLEAR-3K: Assessing Causal Explanatory Capabilities in Language Models
  6. 2023Enhancing Causal Reasoning in Large Language Models: A Causal Attribution Model for Precision Fine-Tuning
  7. 2026CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching
  8. 2025Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discovery