# Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement

arXiv: https://arxiv.org/abs/2402.00745 · HTML: https://mlsanity.com/paper/2402.00745/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 36 of its 53 references that are in the map.
- First posted on arXiv 1 Feb 2024.

## Placed in

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

## Builds on (most cited first, 30 of 36)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers](https://mlsanity.com/paper/2310.15164/) (2023)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [Simple BERT Models for Relation Extraction and Semantic Role Labeling](https://mlsanity.com/paper/1904.05255/) (2019)
- [RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs](https://mlsanity.com/paper/2305.08844/) (2023)
- [INFOTABS: Inference on Tables as Semi-structured Data](https://mlsanity.com/paper/2005.06117/) (2020)
- [TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph](https://mlsanity.com/paper/2104.07302/) (2021)
- [Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph](https://mlsanity.com/paper/2009.11692/) (2020)
- [Generating Natural Language Proofs with Verifier-Guided Search](https://mlsanity.com/paper/2205.12443/) (2022)
- [Self-Verification Improves Few-Shot Clinical Information Extraction](https://mlsanity.com/paper/2306.00024/) (2023)
- [PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training](https://mlsanity.com/paper/2211.02816/) (2022)
- [NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language](https://mlsanity.com/paper/1906.06187/) (2019)
- [Careful Selection of Knowledge to solve Open Book Question Answering](https://mlsanity.com/paper/1907.10738/) (2019)
- [Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable](https://mlsanity.com/paper/2110.13472/) (2021)
- [A Survey on Explainability in Machine Reading Comprehension](https://mlsanity.com/paper/2010.00389/) (2020)
- [FaiRR: Faithful and Robust Deductive Reasoning over Natural Language](https://mlsanity.com/paper/2203.10261/) (2022)
- [Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning](https://mlsanity.com/paper/1909.05803/) (2019)
- [Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering](https://mlsanity.com/paper/2005.01218/) (2020)
- [Modeling Multi-hop Question Answering as Single Sequence Prediction](https://mlsanity.com/paper/2205.09226/) (2022)
- [Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing](https://mlsanity.com/paper/2305.08195/) (2023)
- [Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regeneration](https://mlsanity.com/paper/2107.11879/) (2021)

## Built on by (most cited first, 16 of 16)

- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving](https://mlsanity.com/paper/2405.01379/) (2024)
- [Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions](https://mlsanity.com/paper/2502.12065/) (2025)
- [Consistent Autoformalization for Constructing Mathematical Libraries](https://mlsanity.com/paper/2410.04194/) (2024)
- [Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions](https://mlsanity.com/paper/2502.12616/) (2025)
- [VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks](https://mlsanity.com/paper/2511.04662/) (2025)
- [Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations](https://mlsanity.com/paper/2505.24264/) (2025)
- [Beyond Gold Standards: Epistemic Ensemble of LLM Judges for Formal Mathematical Reasoning](https://mlsanity.com/paper/2506.10903/) (2025)
- [MASA: LLM-Driven Multi-Agent Systems for Autoformalization](https://mlsanity.com/paper/2510.08988/) (2025)
- [LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision](https://mlsanity.com/paper/2512.18196/) (2025)
- [Inference to the Best Explanation in Large Language Models](https://mlsanity.com/paper/2402.10767/) (2024)
- [FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean](https://mlsanity.com/paper/2604.23002/) (2026)
- [Integrating Expert Knowledge into Logical Programs via LLMs](https://mlsanity.com/paper/2502.12275/) (2025)
- [Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs](https://mlsanity.com/paper/2603.09434/) (2026)
- [Compartmentalised Agentic Reasoning for Clinical NLI](https://mlsanity.com/paper/2509.10222/) (2025)
- [Inferring Latent Intentions: Attributional Natural Language Inference in LLM Agents](https://mlsanity.com/paper/2601.08742/) (2026)

## Abstract (arXiv)

An increasing amount of research in Natural Language Inference (NLI) focuses on the application and evaluation of Large Language Models (LLMs) and their reasoning capabilities. Despite their success, however, LLMs are still prone to factual errors and inconsistencies in their explanations, offering limited control and interpretability for inference in complex domains. In this paper, we focus on ethical NLI, investigating how hybrid neuro-symbolic techniques can enhance the logical validity and alignment of ethical explanations produced by LLMs. Specifically, we present an abductive-deductive framework named Logic-Explainer, which integrates LLMs with an external backward-chaining solver to refine step-wise natural language explanations and jointly verify their correctness, reduce incompleteness and minimise redundancy. An extensive empirical analysis demonstrates that Logic-Explainer can improve explanations generated via in-context learning methods and Chain-of-Thought (CoT) on challenging ethical NLI tasks, while, at the same time, producing formal proofs describing and supporting models' reasoning. As ethical NLI requires commonsense reasoning to identify underlying moral violations, our results suggest the effectiveness of neuro-symbolic methods for multi-step NLI more broadly, opening new opportunities to enhance the logical consistency, reliability, and alignment of LLMs.