# From Training to Generalization: Improving Moral Reasoning Through Pragmatic Inference

arXiv: https://arxiv.org/abs/2509.24102 · HTML: https://mlsanity.com/paper/2509.24102/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 14 of its 62 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Placed in

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

## Builds on (most cited first, 14 of 14)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Can Machines Learn Morality? The Delphi Experiment](https://mlsanity.com/paper/2110.07574/) (2021)
- [The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs](https://mlsanity.com/paper/2210.14986/) (2022)
- [Moral Alignment for LLM Agents](https://mlsanity.com/paper/2410.01639/) (2024)
- [Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language](https://mlsanity.com/paper/2503.01539/) (2025)
- [Metaphor and Large Language Models: When Surface Features Matter More than Deep Understanding](https://mlsanity.com/paper/2507.15357/) (2025)
- [Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization](https://mlsanity.com/paper/2502.16600/) (2025)
- [MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking](https://mlsanity.com/paper/2501.13117/) (2025)
- [CDW-CoT: Clustered Distance-Weighted Chain-of-Thoughts Reasoning](https://mlsanity.com/paper/2501.12226/) (2025)
- [Discourse Heuristics For Paradoxically Moral Self-Correction](https://mlsanity.com/paper/2507.00985/) (2025)
- [Diagnosing the Performance Trade-off in Moral Alignment: A Case Study on Gender Stereotypes](https://mlsanity.com/paper/2509.21456/) (2025)

## Built on by (most cited first, 2 of 2)

- [Untangling Input Language from Reasoning Language: A Diagnostic Framework for Cross-Lingual Moral Alignment in LLMs](https://mlsanity.com/paper/2601.10257/) (2026)
- [Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models](https://mlsanity.com/paper/2608.09551/) (2026)

## Abstract (arXiv)

Although moral reasoning has emerged as a promising research direction for large language models (LLMs), a persistent generalization challenge remains: LLMs often achieve strong performance on training data but struggle to generalize their moral reasoning to unseen test data. From a linguistic perspective, moral reasoning is a pragmatic process in which moral judgments are inferred based on the context of social norms underlying a given moral situation. However, existing approaches overlook this pragmatic nature because of two major bottlenecks: (1) LLMs are primarily skilled in capturing distributional semantics, which differs from the pragmatic nature of moral reasoning; (2) there is currently no effective solution for grounding language in the moral context. In this paper, we develop a pragmatic inference approach that enables LLMs to infer moral judgments for a given moral situation by combining metapragmatic links with Moral Foundations Theory. Specifically, metapragmatic links serve to bridge the gap between distributional semantics and pragmatics, whereas Moral Foundations Theory provides a principled basis for grounding language in moral contexts. Experimental results demonstrate that our approach substantially improves LLMs' generalization in moral reasoning, highlighting the potential of pragmatic inference for future moral reasoning research.