Skip to content
conftrace_
2026 EMNLP EMNLP 2026

ExpCSD: Experience-based Debiasing Framework for Conversational Stance Detection Grounded in Latent Thinking Paths

AbstractConversational stance detection, which aims to identify users’ attitudes in conversation threads, has attracted increasing attention in recent years. Yet, mainstream LLM-based approaches remain prone to biases caused by spurious correlations. Existing debiasing methods either rely on indiscriminate multi-step prompting, which can induce unnecessary reasoning and overthinking, or require expensive fine-tuning on curated data. To address these challenges, we propose ExpCSD, an experience-based debiasing framework grounded in latent thinking paths that follows a debias-only-when-needed principle. ExpCSD first assesses whether an LLM’s latent thinking path is biased and selectively retrieves and injects historically similar debiasing experiences only when necessary, without updating model parameters. Experiments on public benchmarks show that ExpCSD outperforms strong baselines in stance detection accuracy while avoiding overthinking and costly fine-tuning.

More from EMNLP 2026

All EMNLP 2026 papers →