Conservative Bias in Large Language Models: Measuring Relation Predictions

ACL ARR 2025 February Submission5085 Authors

Abstract: Large language models (LLMs) exhibit pronounced conservative bias in relation extraction tasks, frequently defaulting to no_relation label when an appropriate option is unavailable. While this behavior helps prevent incorrect relation assignments, our analysis reveals that it also leads to significant information loss when reasoning is not explicitly included in the output. We systematically evaluate this trade-off across multiple prompts, datasets, and relation types, introducing the concept of Hobson's choice to capture scenarios where models opt for safe but uninformative labels over hallucinated ones. Our findings suggest that conservative bias occurs twice as often as hallucination. To quantify this effect, we use SBERT and LLM prompts to capture the semantic similarity between conservative bias behaviors in constrained prompts and labels generated from semi-constrained and open-ended prompts.

Paper Type: Short

Research Area: Information Extraction

Research Area Keywords: LLM, Conservative Bias, Hallucination, Relation Extraction, Semantic Similarity, Prompt Engineering

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data analysis

Languages Studied: English

Submission Number: 5085