A single autoregressive model for conversational recommendation that uses semantic item IDs, predicts response intent and target first, then generates the response, reporting up to 29% Recall@1 gains.
Inspired: Toward sociable recommendation dialog systems
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
In recommendation dialogs, humans commonly disclose their preference and make recommendations in a friendly manner. However, this is a challenge when developing a sociable recommendation dialog system, due to the lack of dialog dataset annotated with such sociable strategies. Therefore, we present INSPIRED, a new dataset of 1,001 human-human dialogs for movie recommendation with measures for successful recommendations. To better understand how humans make recommendations in communication, we design an annotation scheme related to recommendation strategies based on social science theories and annotate these dialogs. Our analysis shows that sociable recommendation strategies, such as sharing personal opinions or communicating with encouragement, more frequently lead to successful recommendations. Based on our dataset, we train end-to-end recommendation dialog systems with and without our strategy labels. In both automatic and human evaluation, our model with strategy incorporation outperforms the baseline model. This work is a first step for building sociable recommendation dialog systems with a basis of social science theories.
citation-role summary
dataset 1
citation-polarity summary
fields
cs.IR 4years
2026 4roles
dataset 1polarities
use dataset 1representative citing papers
RAR retrieves candidate items from a 300k-movie corpus then uses LLM generation with RL feedback to produce context-aware recommendations that outperform baselines on benchmarks.
SMTPO uses multi-task SFT to improve simulator feedback quality and RL with fine-grained rewards to optimize multi-turn preference reasoning in LLM-based conversational recommendation.
Optimal preference elicitation in conversational recommenders is stage-dependent (attributes early, items later), and a MoE model trained on a new annotated dataset improves offline recommendation and response quality.
citing papers explorer
-
Generative Conversational Recommender System
A single autoregressive model for conversational recommendation that uses semantic item IDs, predicts response intent and target first, then generates the response, reporting up to 29% Recall@1 gains.
-
Retrieval Augmented Conversational Recommendation with Reinforcement Learning
RAR retrieves candidate items from a 300k-movie corpus then uses LLM generation with RL feedback to produce context-aware recommendations that outperform baselines on benchmarks.
-
User Simulator-Guided Multi-Turn Preference Optimization for Reasoning LLM-based Conversational Recommendation
SMTPO uses multi-task SFT to improve simulator feedback quality and RL with fine-grained rewards to optimize multi-turn preference reasoning in LLM-based conversational recommendation.
-
When and How to Ask: Dynamic Preference Elicitation Strategies for Conversational Recommendation
Optimal preference elicitation in conversational recommenders is stage-dependent (attributes early, items later), and a MoE model trained on a new annotated dataset improves offline recommendation and response quality.