# Generating Effective CoT Traces for Mitigating Causal Hallucination

arXiv: https://arxiv.org/abs/2604.12748 · HTML: https://mlsanity.com/paper/2604.12748/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning.
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Placed in

- LLM reasoning / [Hallucination detection and mitigation](https://mlsanity.com/lr/hallucination-detection-and-mitigation/)

## Builds on (most cited first, 7 of 7)

- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [Small Models Struggle to Learn from Strong Reasoners](https://mlsanity.com/paper/2502.12143/) (2025)
- [Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation](https://mlsanity.com/paper/2305.07375/) (2023)
- [The Best Instruction-Tuning Data are Those That Fit](https://mlsanity.com/paper/2502.04194/) (2025)
- [A Survey of Event Causality Identification: Taxonomy, Challenges, Assessment, and Prospects](https://mlsanity.com/paper/2411.10371/) (2024)
- [Data Selection for Multi-turn Dialogue Instruction Tuning](https://mlsanity.com/paper/2604.07892/) (2026)
- [Instruction Data Selection via Answer Divergence](https://mlsanity.com/paper/2604.10448/) (2026)

## Abstract (arXiv)

Although large language models (LLMs) excel in complex reasoning tasks, they suffer from severe causal hallucination in event causality identification (ECI), particularly in smaller models (≤1.5B parameters). A promising approach to address this issue is to fine-tune them with Chain-of-Thought (CoT) traces. However, there is currently a lack of CoT trace dataset available for ECI. In this paper, we first investigate the essential criteria that effective CoT traces should possess to mitigate causal hallucination in smaller models. We then design a pipeline to generate CoT traces that meet these criteria. Moreover, since there is currently no metric for quantifying causal hallucination, we also introduce a new metric, the Causal Hallucination Rate (CHR), to quantify causal hallucination, guide the formulation of effective CoT trace criteria, and validate the effectiveness of our pipeline. Our experiments show that fine-tuning with the CoT traces generated by our pipeline not only substantially reduces causal hallucination in smaller LLMs but also improves mean accuracy. Moreover, the fine-tuned models exhibit strong cross-dataset and cross-difficulty generalization, as well as robustness under misleading intervention prompts.