DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913757172596736 |
|---|---|
| author | Bae, Suyoung Choi, YunSeok Lee, Jee-Hyong |
| author_facet | Bae, Suyoung Choi, YunSeok Lee, Jee-Hyong |
| contents | While Large Language Models (LLMs) excel in zero-shot Question Answering (QA), they tend to expose biases in their internal knowledge when faced with socially sensitive questions, leading to a degradation in performance. Existing zero-shot methods are efficient but fail to consider context and prevent bias propagation in the answers. To address this, we propose DeCAP, a method for debiasing LLMs using Context-Adaptive Prompt Generation. DeCAP leverages a Question Ambiguity Detection to take appropriate debiasing actions based on the context and a Neutral Answer Guidance Generation to suppress the LLMs make objective judgments about the context, minimizing the propagation of bias from their internal knowledge. Our various experiments across eight LLMs show that DeCAP achieves state-of-the-art zero-shot debiased QA performance. This demonstrates DeCAP's efficacy in enhancing the fairness and accuracy of LLMs in diverse QA settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19426 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models Bae, Suyoung Choi, YunSeok Lee, Jee-Hyong Computation and Language Artificial Intelligence Computers and Society While Large Language Models (LLMs) excel in zero-shot Question Answering (QA), they tend to expose biases in their internal knowledge when faced with socially sensitive questions, leading to a degradation in performance. Existing zero-shot methods are efficient but fail to consider context and prevent bias propagation in the answers. To address this, we propose DeCAP, a method for debiasing LLMs using Context-Adaptive Prompt Generation. DeCAP leverages a Question Ambiguity Detection to take appropriate debiasing actions based on the context and a Neutral Answer Guidance Generation to suppress the LLMs make objective judgments about the context, minimizing the propagation of bias from their internal knowledge. Our various experiments across eight LLMs show that DeCAP achieves state-of-the-art zero-shot debiased QA performance. This demonstrates DeCAP's efficacy in enhancing the fairness and accuracy of LLMs in diverse QA settings. |
| title | DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models |
| topic | Computation and Language Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2503.19426 |