# Neutralizing Bias in LLM Reasoning using Entailment Graphs

arXiv: https://arxiv.org/abs/2503.11614 · HTML: https://mlsanity.com/paper/2503.11614/

## 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 8 of its 42 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Placed in

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

## Builds on (most cited first, 8 of 8)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Large Language Models and Causal Inference in Collaboration: A Survey](https://mlsanity.com/paper/2403.09606/) (2024)
- [Probabilistic Models of Relational Implication](https://mlsanity.com/paper/1907.12048/) (2019)
- [AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation](https://mlsanity.com/paper/2402.10646/) (2024)
- [A Comprehensive Survey of Contamination Detection Methods in Large Language Models](https://mlsanity.com/paper/2404.00699/) (2024)
- [Using Natural Language Explanations to Improve Robustness of In-context Learning](https://mlsanity.com/paper/2311.07556/) (2023)

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

- [Where Should I Study? Biased Language Models Decide! Evaluating Fairness in LMs for Academic Recommendations](https://mlsanity.com/paper/2509.04498/) (2025)
- [Evaluating Multilingual and Code-Switched Alignment in LLMs via Synthetic Natural Language Inference](https://mlsanity.com/paper/2508.14735/) (2025)
- [LLMs are Frequency Pattern Learners in Natural Language Inference](https://mlsanity.com/paper/2505.21011/) (2025)

## Abstract (arXiv)

LLMs are often claimed to be capable of Natural Language Inference (NLI), which is widely regarded as a cornerstone of more complex forms of reasoning. However, recent works show that LLMs still suffer from hallucinations in NLI due to attestation bias, where LLMs overly rely on propositional memory to build shortcuts. To solve the issue, we design an unsupervised framework to construct counterfactual reasoning data and fine-tune LLMs to reduce attestation bias. To measure bias reduction, we build bias-adversarial variants of NLI datasets with randomly replaced predicates in premises while keeping hypotheses unchanged. Extensive evaluations show that our framework can significantly reduce hallucinations from attestation bias. Then, we further evaluate LLMs fine-tuned with our framework on original NLI datasets and their bias-neutralized versions, where original entities are replaced with randomly sampled ones. Extensive results show that our framework consistently improves inferential performance on both original and bias-neutralized NLI datasets.