Saved in:
Bibliographic Details
Main Authors: Zhao, Yiheng, Yan, Jun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.12748
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918446086750208
author Zhao, Yiheng
Yan, Jun
author_facet Zhao, Yiheng
Yan, Jun
contents 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 ($\leq$1.5B parameters). A promising approach to address this issue is to fine-tune them with Chain-of-Thought (CoT) traces. However, there is currently a lack of CoT trace dataset available for ECI. In this paper, we first investigate the essential criteria that effective CoT traces should possess to mitigate causal hallucination in smaller models. We then design a pipeline to generate CoT traces that meet these criteria. Moreover, since there is currently no metric for quantifying causal hallucination, we also introduce a new metric, the Causal Hallucination Rate (CHR), to quantify causal hallucination, guide the formulation of effective CoT trace criteria, and validate the effectiveness of our pipeline. Our experiments show that fine-tuning with the CoT traces generated by our pipeline not only substantially reduces causal hallucination in smaller LLMs but also improves mean accuracy. Moreover, the fine-tuned models exhibit strong cross-dataset and cross-difficulty generalization, as well as robustness under misleading intervention prompts.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12748
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generating Effective CoT Traces for Mitigating Causal Hallucination
Zhao, Yiheng
Yan, Jun
Computation and Language
Although large language models (LLMs) excel in complex reasoning tasks, they suffer from severe causal hallucination in event causality identification (ECI), particularly in smaller models ($\leq$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.
title Generating Effective CoT Traces for Mitigating Causal Hallucination
topic Computation and Language
url https://arxiv.org/abs/2604.12748