Collaborative Parameter Learning freezes 50-75% of parameters whose updates cause forgetting and updates only the 25-50% that mitigate it, allowing LLMs to learn 20-48% more new questions with negligible forgetting and lower compute cost.
An information bottleneck perspective for effective noise filtering on retrieval-augmented generation.arXiv preprint arXiv:2406.01549
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
TinyAlign improves lightweight VLMs by retrieving compressed image-text memory items to augment visual inputs, claiming large loss and data-efficiency gains, but the memory bank is sampled from the training captions, raising a label-leakage concern.
AdaComp trains a compression-rate predictor on annotated minimum top-k data to adaptively retain only the documents needed for each RAG query.
A review that organizes RAG evaluation into internal and external categories, catalogs dozens of benchmarks, and analyzes evaluation practices in 582 conference papers.
citing papers explorer
-
Collaborative Parameter Learning: Mitigating Forgetting via Parameter-Level Gradient Analysis
Collaborative Parameter Learning freezes 50-75% of parameters whose updates cause forgetting and updates only the 25-50% that mitigate it, allowing LLMs to learn 20-48% more new questions with negligible forgetting and lower compute cost.
-
TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks
TinyAlign improves lightweight VLMs by retrieving compressed image-text memory items to augment visual inputs, claiming large loss and data-efficiency gains, but the memory bank is sampled from the training captions, raising a label-leakage concern.
-
AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models
AdaComp trains a compression-rate predictor on annotated minimum top-k data to adaptively retain only the documents needed for each RAG query.
-
Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey
A review that organizes RAG evaluation into internal and external categories, catalogs dozens of benchmarks, and analyzes evaluation practices in 582 conference papers.