REVIEW 10 cited by
A Large Language Model Enhanced Conversational Recommender System
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Conversational recommender systems (CRSs) aim to recommend high-quality items to users through a dialogue interface. It usually contains multiple sub-tasks, such as user preference elicitation, recommendation, explanation, and item information search. To develop effective CRSs, there are some challenges: 1) how to properly manage sub-tasks; 2) how to effectively solve different sub-tasks; and 3) how to correctly generate responses that interact with users. Recently, Large Language Models (LLMs) have exhibited an unprecedented ability to reason and generate, presenting a new opportunity to develop more powerful CRSs. In this work, we propose a new LLM-based CRS, referred to as LLMCRS, to address the above challenges. For sub-task management, we leverage the reasoning ability of LLM to effectively manage sub-task. For sub-task solving, we collaborate LLM with expert models of different sub-tasks to achieve the enhanced performance. For response generation, we utilize the generation ability of LLM as a language interface to better interact with users. Specifically, LLMCRS divides the workflow into four stages: sub-task detection, model matching, sub-task execution, and response generation. LLMCRS also designs schema-based instruction, demonstration-based instruction, dynamic sub-task and model matching, and summary-based generation to instruct LLM to generate desired results in the workflow. Finally, to adapt LLM to conversational recommendations, we also propose to fine-tune LLM with reinforcement learning from CRSs performance feedback, referred to as RLPF. Experimental results on benchmark datasets show that LLMCRS with RLPF outperforms the existing methods.
Forward citations
Cited by 10 Pith papers
-
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.
-
ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning
ReRec uses reinforcement fine-tuning with dual-graph reward shaping, reasoning-aware advantage estimation, and online curriculum scheduling to improve LLM reasoning and performance in recommendation tasks.
-
LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models
An LLM-driven agent generates synthetic interaction sequences that, when queried against a target sequential recommender, produce surrogate models with higher agreement to the target than random or autoregressive data...
-
Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent
TAIRA, a thought-pattern-augmented multi-agent recommender, outperforms prior LLM agents in simulated interactive recommendation, with the largest gains on complex user intents.
-
Dialogue to Discovery: Attribute-Aware Preference Elicitation for Conversational Product Search Assistants
D2D adaptively prioritizes informative attribute queries and times recommendations in conversational search, yielding 22-30% higher target accuracy and shorter conversations than baselines in simulations.
-
CESRec: Constructing Pseudo Interactions for Sequential Recommendation via Conversational Feedback
CESRec improves sequential recommenders by converting simulated user feedback into edited pseudo-interaction sequences and masking outlier items, with gains reported on three benchmarks.
-
Modeling shopper interest broadness with entropy-driven dialogue policy in the context of arbitrarily large product catalogs
Retrieval-score entropy, normalized over the top 50 candidates, routes a conversational recommender between direct recommendations and clarifying questions, and the production AB test shows longer conversations.
-
Rethinking Group Recommender Systems in the Era of Generative AI: From One-Shot Recommendations to Agentic Group Decision Support
The paper proposes reorienting group recommender systems from one-shot preference aggregation to chat-based, agentic decision support powered by large language models.
-
On Mitigating Data Sparsity in Conversational Recommender Systems
DACRS combines LLM-based dialogue augmentation, knowledge-graph entity substitution, and an entity similarity constraint to improve conversational recommendation accuracy on ReDial and Inspired.
-
A Scenario-Oriented Survey of Federated Recommender Systems: Techniques, Challenges, and Future Directions
A scenario-oriented taxonomy of federated recommender systems that argues research should be organized around recommendation use cases rather than federated-learning abstractions.
Discussion (0). Sign in to comment.