# Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door Adjustment

arXiv: https://arxiv.org/abs/2508.16910 · HTML: https://mlsanity.com/paper/2508.16910/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 9 of its 52 references that are in the map.
- First posted on arXiv 23 Aug 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 9 of 9)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [Investigating the Catastrophic Forgetting in Multimodal Large Language Models](https://mlsanity.com/paper/2309.10313/) (2023)
- [Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning](https://mlsanity.com/paper/2410.14211/) (2024)
- [How Likely Do LLMs with CoT Mimic Human Reasoning?](https://mlsanity.com/paper/2402.16048/) (2024)
- [WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus](https://mlsanity.com/paper/2304.04358/) (2023)
- [Causal Prompting for Implicit Sentiment Analysis with Large Language Models](https://mlsanity.com/paper/2507.00389/) (2025)
- [Furthest Reasoning with Plan Assessment: Stable Reasoning Path with Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2309.12767/) (2023)

## Built on by (most cited first, 6 of 6)

- [When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.09241/) (2026)
- [When to Invoke: Refining LLM Fairness with Toxicity Assessment](https://mlsanity.com/paper/2601.09250/) (2026)
- [Bridging Semantic Understanding and Popularity Bias with LLMs](https://mlsanity.com/paper/2601.09478/) (2026)
- [Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning](https://mlsanity.com/paper/2608.28018/) (2026)
- [Harnessing LLM for Noise-Robust Cognitive Diagnosis in Web-Based Intelligent Education Systems](https://mlsanity.com/paper/2510.04093/) (2025)
- [The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining](https://mlsanity.com/paper/2609.32964/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have shown impressive capabilities in natural language processing but still struggle to perform well on knowledge-intensive tasks that require deep reasoning and the integration of external knowledge. Although methods such as Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) have been proposed to enhance LLMs with external knowledge, they still suffer from internal bias in LLMs, which often leads to incorrect answers. In this paper, we propose a novel causal prompting framework, Conditional Front-Door Prompting (CFD-Prompting), which enables the unbiased estimation of the causal effect between the query and the answer, conditional on external knowledge, while mitigating internal bias. By constructing counterfactual external knowledge, our framework simulates how the query behaves under varying contexts, addressing the challenge that the query is fixed and is not amenable to direct causal intervention. Compared to the standard front-door adjustment, the conditional variant operates under weaker assumptions, enhancing both robustness and generalisability of the reasoning process. Extensive experiments across multiple LLMs and benchmark datasets demonstrate that CFD-Prompting significantly outperforms existing baselines in both accuracy and robustness.