7 papers
Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs
Weiwei Ding, Zixuan Li, Long Bai +7
Knowledge Graphs (KGs) are widely used to mitigate the limitations of Large Language Models (LLMs), such as outdated knowledge and hallucinations. Existing LLM-KG integration frame…
Knowledge Capsules: Structured Nonparametric Memory Units for LLMs
Bin Ju, Shenfeng Weng, Danying Zhou +2
Large language models (LLMs) encode knowledge in parametric weights, making it costly to update or extend without retraining. Retrieval-augmented generation (RAG) mitigates this li…
Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion
Pengcheng Jiang, Judith Yue Li, Moonkyung Ryu +8
Many modern retrieval problems are set-valued: given a broad intent, the system must return a collection of results that optimizes higher-order properties (e.g., diversity, coverag…
Efficient Item ID Generation for Large-Scale LLM-based Recommendation
Anushya Subbiah, Vikram Aggarwal, James Pine +3
Integrating product catalogs and user behavior into LLMs can enhance recommendations with broad world knowledge, but the scale of real-world item catalogs, often containing million…
REGEN: A Dataset and Benchmarks with Natural Language Critiques and Narratives
Kun Su, Krishna Sayana, Hubert Pham +8
This paper introduces a novel dataset REGEN (Reviews Enhanced with GEnerative Narratives), designed to benchmark the conversational capabilities of recommender Large Language Model…
Beyond Retrieval: Generating Narratives in Conversational Recommender Systems
Krishna Sayana, Raghavendra Vasudeva, Yuri Vasilevski +6
The recent advances in Large Language Model's generation and reasoning capabilities present an opportunity to develop truly conversational recommendation systems. However, effectiv…