How to Enhance Causal Discrimination of Utterances: A Case on Affective Reasoning
This work addresses the problem of improving causal reasoning in conversational AI for affective tasks, representing an incremental advance by introducing a novel method for a known bottleneck in existing models.
The paper tackles the challenge of causal discrimination in Affective Reasoning in Conversation (ARC), where existing models capture semantic correlations but fail to determine specific causal relationships, and proposes a structural causal model with i.i.d. noise and an autoencoder architecture, achieving validated effectiveness and interpretability in experiments.
Our investigation into the Affective Reasoning in Conversation (ARC) task highlights the challenge of causal discrimination. Almost all existing models, including large language models (LLMs), excel at capturing semantic correlations within utterance embeddings but fall short in determining the specific causal relationships. To overcome this limitation, we propose the incorporation of \textit{i.i.d.} noise terms into the conversation process, thereby constructing a structural causal model (SCM). It explores how distinct causal relationships of fitted embeddings can be discerned through independent conditions. To facilitate the implementation of deep learning, we introduce the cogn frameworks to handle unstructured conversation data, and employ an autoencoder architecture to regard the unobservable noise as learnable "implicit causes." Moreover, we curate a synthetic dataset that includes i.i.d. noise. Through comprehensive experiments, we validate the effectiveness and interpretability of our approach. Our code is available in https://github.com/Zodiark-ch/mater-of-our-EMNLP2023-paper.