Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization

Chen, Liang Chu; Wang, Hongru; Deng, Yang; Kwan, W.; Wang, Zezhong; Wong, Kam-Fai

doi:10.18653/v1/2023.findings-acl.462

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dialogue System. Most of the previous work develops personalized (Zhang et al, 2018;Zheng et al, 2020;Song et al, 2021;Chen et al, 2023a), emotional (Ghosal et al, 2020;Zheng et al, 2023a;Deng et al, 2023c;Zheng et al, 2023b), empathetic (Rashkin et al, 2019Sabour et al, 2022) dialogue system in isolation, rather than seamlessly blending them all into one cohesive conversational flow (Smith et al, 2020;. A common approach is to predict the emotion or persona from a pre-defined set and generate the response in a multi-task manner (Ma et al, 2021;Sabour et al, 2022;.…”

Section: Related Workmentioning

confidence: 99%

Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs

Wang,

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

Large Language Models (LLMs), such as ChatGPT, greatly empower dialogue systems with strong language understanding and generation capabilities. However, most of the previous works prompt the LLMs to directly generate a response based on the dialogue context, overlooking the underlying linguistic cues about the user status exhibited in the context. Such in-depth dialogue scenarios are challenging for existing LLMs to figure out the user's hidden needs and respond satisfactorily through a single-step inference. To this end, we propose a novel linguistic cue-based chain-of-thoughts (Cue-CoT), which enhances the LLMs inference with an intermediate reasoning step to find cues exhibited in the dialogue, aiming to provide a more personalized and engaging response. To evaluate the approach, we build a benchmark with in-depth dialogue questions, consisting of 6 datasets in both Chinese and English, targeting 3 major linguistic cues during the conversation: personality, emotion, and psychology. We conduct extensive experiments on the proposed benchmark with 5 LLMs under both zero-shot and one-shot settings. Empirical results demonstrate our proposed Cue-CoT method outperforms standard prompting methods in terms of both helpfulness and acceptability on all datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs

Wang,

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

show abstract

Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization

Cited by 1 publication

References 0 publications

Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs

Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs

Contact Info

Product

Resources

About