# Computational models of pragmatic reasoning with flexible generation of meaning and expression alternatives

arXiv: https://arxiv.org/abs/2607.18443 · HTML: https://mlsanity.com/paper/2607.18443/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 23 of its 125 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 23 of 23)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022)
- [Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4](https://mlsanity.com/paper/2304.03439/) (2023)
- [ART: Automatic multi-step reasoning and tool-use for large language models](https://mlsanity.com/paper/2303.09014/) (2023)
- [LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks](https://mlsanity.com/paper/2402.01817/) (2024)
- [Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve](https://mlsanity.com/paper/2309.13638/) (2023)
- [Solving Math Word Problems by Combining Language Models With Symbolic Solvers](https://mlsanity.com/paper/2304.09102/) (2023)
- [Turning large language models into cognitive models](https://mlsanity.com/paper/2306.03917/) (2023)
- [How Linguistics Learned to Stop Worrying and Love the Language Models](https://mlsanity.com/paper/2501.17047/) (2025)
- [Centaur: a foundation model of human cognition](https://mlsanity.com/paper/2410.20268/) (2024)
- [Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models](https://mlsanity.com/paper/2507.12547/) (2025)
- [Non-literal Understanding of Number Words by Language Models](https://mlsanity.com/paper/2502.06204/) (2025)
- [Using LLMs to Advance the Cognitive Science of Collectives](https://mlsanity.com/paper/2506.00052/) (2025)
- [Cognitive Modeling with Scaffolded LLMs: A Case Study of Referential Expression Generation](https://mlsanity.com/paper/2407.03805/) (2024)

## Abstract (arXiv)

Pragmatic language use requires reasoning about alternatives: the alternative expressions a speaker might have chosen, or the alternative interpretations a listener might entertain. Formal and computational models of pragmatics must therefore specify the sets of alternatives that interlocutors reason over, which is often done through manual specification. Here we propose a framework, ScAffolded Generative models for Explanation (SAGE), that combines the explanatory transparency of cognitive models with the generative flexibility of language models (LMs). SAGE decomposes a pragmatic process into three kinds of modules: proposers, which use LMs to generate an open-ended space of candidate alternatives; evaluators, which assess those alternatives (e.g., their semantics, complexity, or typicality); and selectors, which implement the rule-based computational steps of a cognitively motivated task analysis. We assess SAGE in three case studies spanning pragmatic generation and interpretation-referential expression generation, manner (M-)implicatures, and Gricean conversational implicatures. SAGE models are evaluated critically using established methods from computational cognitive modeling, including ablations, baseline comparisons, and quantitative fit to human data. Across studies, SAGE models achieved high accuracy and often outperformed baselines, but component-level analyses reveal an asymmetry: LM proposers reliably generated alternatives well-suited to pragmatic modeling, whereas LM evaluators are better at providing intuitive judgements rather than judgements of theoretical or formal measures. We discuss the promise and the limitations of neuro-symbolic models as candidate explanatory accounts of human pragmatic language use.