"It doesn't look good for a date": Transforming Critiques into Preferences for Conversational Recommendation Systems
This work addresses the challenge of making conversational recommendation systems more intuitive for users by handling natural language critiques, though it is incremental as it builds on existing language model methods.
The paper tackles the problem of interpreting user critiques in conversational recommendation systems by transforming them into positive preferences to improve recommendation retrieval, showing that this transformation enhances recommendations in the restaurant domain.
Conversations aimed at determining good recommendations are iterative in nature. People often express their preferences in terms of a critique of the current recommendation (e.g., "It doesn't look good for a date"), requiring some degree of common sense for a preference to be inferred. In this work, we present a method for transforming a user critique into a positive preference (e.g., "I prefer more romantic") in order to retrieve reviews pertaining to potentially better recommendations (e.g., "Perfect for a romantic dinner"). We leverage a large neural language model (LM) in a few-shot setting to perform critique-to-preference transformation, and we test two methods for retrieving recommendations: one that matches embeddings, and another that fine-tunes an LM for the task. We instantiate this approach in the restaurant domain and evaluate it using a new dataset of restaurant critiques. In an ablation study, we show that utilizing critique-to-preference transformation improves recommendations, and that there are at least three general cases that explain this improved performance.