Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task

TL;DR

This paper introduces Pneg, a prompt-based method using large language models to generate adversarial negative responses, improving dialogue response selection models without costly human annotation.

Contribution

Proposes a scalable, prompt-based approach leveraging large language models to generate adversarial negatives for dialogue response selection, outperforming existing methods.

Findings

Outperforms other adversarial response synthesis methods

Effective alternative to human-generated adversarial responses

Enhances the discriminative power of response selection models

Abstract

In retrieval-based dialogue systems, a response selection model acts as a ranker to select the most appropriate response among several candidates. However, such selection models tend to rely on context-response content similarity, which makes models vulnerable to adversarial responses that are semantically similar but not relevant to the dialogue context. Recent studies have shown that leveraging these adversarial responses as negative training samples is useful for improving the discriminating power of the selection model. Nevertheless, collecting human-written adversarial responses is expensive, and existing synthesizing methods often have limited scalability. To overcome these limitations, this paper proposes a simple but efficient method for generating adversarial negative responses leveraging a large-scale language model. Experimental results on dialogue selection tasks show that our method outperforms other methods of synthesizing adversarial negative responses. These results suggest that our method can be an effective alternative to human annotators in generating adversarial responses. Our dataset and generation code is available at https://github.com/leenw23/generating-negatives-by-gpt3.