PURE reduces preference-inconsistent explanations in LLM recommenders by selecting user-aligned evidence paths and injecting them into generation, while preserving accuracy.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
Time-RA reformulates time series anomaly detection as a reasoning-intensive generative task and provides the RATs40K multimodal benchmark to evaluate and improve LLM-based diagnosis.
OR-VSKC provides 28,190 synthetic operating room images plus an expert subset to expose and reduce visual-semantic knowledge conflicts in multimodal models for surgical risk detection.
GRACE dynamically constructs and updates coresets for LLM training using representation diversity, gradient-based importance, and k-NN graph propagation to improve efficiency and performance.
B4DL provides a new benchmark, scalable data generation pipeline, and MLLM architecture for direct spatio-temporal reasoning on raw 4D LiDAR data.
PiKV proposes expert-sharded KV storage, PiKV routing, adaptive scheduling, and compression modules to reduce overhead in multi-GPU MoE inference.
citing papers explorer
-
Beyond Factual Correctness: Mitigating Preference-Inconsistent Explanations in Explainable Recommendation
PURE reduces preference-inconsistent explanations in LLM recommenders by selecting user-aligned evidence paths and injecting them into generation, while preserving accuracy.
-
Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback
Time-RA reformulates time series anomaly detection as a reasoning-intensive generative task and provides the RATs40K multimodal benchmark to evaluate and improve LLM-based diagnosis.
-
OR-VSKC: Resolving Visual-Semantic Knowledge Conflicts in Operating Rooms with Synthetic Data-Guided Alignment
OR-VSKC provides 28,190 synthetic operating room images plus an expert subset to expose and reduce visual-semantic knowledge conflicts in multimodal models for surgical risk detection.
-
GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization
GRACE dynamically constructs and updates coresets for LLM training using representation diversity, gradient-based importance, and k-NN graph propagation to improve efficiency and performance.
-
B4DL: A Benchmark for 4D LiDAR LLM in Spatio-Temporal Understanding
B4DL provides a new benchmark, scalable data generation pipeline, and MLLM architecture for direct spatio-temporal reasoning on raw 4D LiDAR data.
-
PiKV: KV Cache Management System for Mixture of Experts
PiKV proposes expert-sharded KV storage, PiKV routing, adaptive scheduling, and compression modules to reduce overhead in multi-GPU MoE inference.