mlsanityData to 14 Oct 2026

Integrating Neural and Symbolic Components in a Model of Pragmatic Question-Answering

arXiv 2506.01474 ↗First posted 2 Jun 2025cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Computational models of pragmatic language use have traditionally relied on hand-specified sets of utterances and meanings, limiting their applicability to real-world language use. We propose a neuro-symbolic framework that enhances probabilistic cognitive models by integrating LLM-based modules to propose and evaluate key components in natural language, eliminating the need for manual specification. Through a classic case study of pragmatic question-answering, we systematically examine various approaches to incorporating neural modules into the cognitive model -- from evaluating utilities and literal semantics to generating alternative utterances and goals. We find that hybrid models can match or exceed the performance of traditional probabilistic models in predicting human answer patterns. However, the success of the neuro-symbolic model depends critically on how LLMs are integrated: while they are particularly effective for proposing alternatives and transforming abstract goals into utilities, they face challenges with truth-conditional semantic evaluation. This work charts a path toward more flexible and scalable models of pragmatic language use while illuminating crucial design considerations for balancing neural and symbolic components.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 20 of its 57 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

20 of 57 references.

References · 20

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  6. 2024LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Taskscited by 243
  7. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 179
  8. 2024Distilling System 2 into System 1cited by 159
  9. 2023Solving Math Word Problems by Combining Language Models With Symbolic Solverscited by 124
  10. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thoughtcited by 119
  11. 2024STaR-GATE: Teaching Language Models to Ask Clarifying Questionscited by 104
  12. 2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85
8 more
  1. 2023Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programscited by 80
  2. 2022The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMscited by 58
  3. 2022Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning taskscited by 56
  4. 2020Learning to refer informatively by amortizing pragmatic reasoningcited by 17
  5. 2017Question Asking as Program Generationcited by 13
  6. 2024Bayesian Statistical Modeling with Predictors from LLMscited by 7
  7. 2024Experimental Pragmatics with Machines: Testing LLM Predictions for the Inferences of Plain and Embedded Disjunctionscited by 5
  8. 2024Cognitive Modeling with Scaffolded LLMs: A Case Study of Referential Expression Generationcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Cognitive models can reveal interpretable value trade-offs in language modelscited by 3