Victor Bursztyn, Jennifer Healey, Doug Downey, Nedim Lipka, Larry Birnbaum, Eunyee Koh
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 fewshot 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 critiqueto-preference transformation improves recommendations, and that there are at least three general cases that explain this improved performance.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.07576")
get_code_for_paper("2109.07576")
have("2109.07576")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2109.07576.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2109.07576)
Connect an agent — have() is free.