# Understand the Implication: Learning to Think for Pragmatic Understanding

arXiv: https://arxiv.org/abs/2506.13559 · HTML: https://mlsanity.com/paper/2506.13559/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Placed in

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

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive](https://mlsanity.com/paper/2402.13228/) (2024)
- [System 2 Attention (is something you might need too)](https://mlsanity.com/paper/2311.11829/) (2023)
- [Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective](https://mlsanity.com/paper/2404.04626/) (2024)
- [PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities](https://mlsanity.com/paper/2401.07078/) (2024)
- ["I'd rather just go to bed": Understanding Indirect Answers](https://mlsanity.com/paper/2010.03450/) (2020)
- [Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding](https://mlsanity.com/paper/2310.19671/) (2023)
- [Harnessing the linguistic signal to predict scalar inferences](https://mlsanity.com/paper/1910.14254/) (2019)
- [SQUINKY! A Corpus of Sentence-level Formality, Informativeness, and Implicature](https://mlsanity.com/paper/1506.02306/) (2015)

## Built on by (most cited first, 3 of 3)

- [Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMs](https://mlsanity.com/paper/2604.04177/) (2026)
- [When Contextual Inference Fails: Cancelability in Interactive Instruction Following](https://mlsanity.com/paper/2603.19997/) (2026)
- [DRInQ: Evaluating Conversational Implicature with Controlled Context Variation](https://mlsanity.com/paper/2605.24267/) (2026)

## Abstract (arXiv)

Pragmatics, the ability to infer meaning beyond literal interpretation, is crucial for social cognition and communication. While LLMs have been benchmarked for their pragmatic understanding, improving their performance remains underexplored. Existing methods rely on annotated labels but overlook the reasoning process humans naturally use to interpret implicit meaning. To bridge this gap, we introduce a novel pragmatic dataset, ImpliedMeaningPreference, that includes explicit reasoning (thoughts) for both correct and incorrect interpretations. Through preference-tuning and supervised fine-tuning, we demonstrate that thought-based learning significantly enhances LLMs' pragmatic understanding, improving accuracy by 11.12% across model families. We further discuss a transfer-learning study where we evaluate the performance of thought-based training for the other tasks of pragmatics (presupposition, deixis) that are not seen during the training time and observe an improvement of 16.10% compared to label-trained models.