Xiaofei Wen
2024
Red Teaming Language Models for Processing Contradictory Dialogues
Xiaofei Wen
|
Bangzheng Li
|
Tenghao Huang
|
Muhao Chen
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Most language models currently available are prone to self-contradiction during dialogues. To mitigate this issue, this study explores a novel contradictory dialogue processing task that aims to detect and modify contradictory statements in a conversation. This task is inspired by research on context faithfulness and dialogue comprehension, which have demonstrated that the detection and understanding of contradictions often necessitate detailed explanations. We develop a dataset comprising contradictory dialogues, in which one side of the conversation contradicts itself. Each dialogue is accompanied by an explanatory label that highlights the location and details of the contradiction. With this dataset, we present a Red Teaming framework for contradictory dialogue processing. The framework detects and attempts to explain the dialogue, then modifies the existing contradictory content using the explanation. Our experiments demonstrate that the framework improves the ability to detect contradictory dialogues and provides valid explanations. Additionally, it showcases distinct capabilities for modifying such dialogues. Our study highlights the importance of the logical inconsistency problem in conversational AI.
Personalized Topic Selection Model for Topic-Grounded Dialogue
Shixuan Fan
|
Wei Wei
|
Xiaofei Wen
|
Xian-Ling Mao
|
Jixiong Chen
|
Dangyang Chen
Findings of the Association for Computational Linguistics: ACL 2024
Recently, the topic-grounded dialogue (TGD) system has become increasingly popular as its powerful capability to actively guide users to accomplish specific tasks through topic-guided conversations. Most existing works utilize side information (e.g. topics or personas) in isolation to enhance the topic selection ability. However, due to disregarding the noise within these auxiliary information sources and their mutual influence, current models tend to predict user-uninteresting and contextually irrelevant topics. To build user-engaging and coherent dialogue agent, we propose a personalized topic selection model for topic-grounded dialogue, named PETD, which takes account of the interaction of side information to selectively aggregate such information for more accurately predicting subsequent topics. Specifically, we evaluate the correlation between global topics and personas and selectively incorporate the global topics aligned with user personas. Furthermore, we propose a contrastive learning based persona selector to filter relevant personas under the constraint of lacking pertinent persona annotations. Throughout the selection and generation, diverse relevant side information is considered. Extensive experiments demonstrate that our proposed method can generate engaging and diverse responses, outperforming state-of-the-art baselines across various evaluation metrics.
Search
Co-authors
- Bangzheng Li 1
- Tenghao Huang 1
- Muhao Chen 1
- Shixuan Fan 1
- Wei Wei 1
- show all...