At 60% SparseGPT sparsity, mixing four capability-matched calibration corpora preserves 58.8% of unpruned performance versus 40.0% for C4 — but the mix is partially calibrated on the same GSM8K and MBPP benchmarks used for evaluation.
arXiv preprint arXiv:2402.09748 (2024)
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Empirical tests show compressed code language models retain task performance but suffer markedly lower robustness under four standard adversarial attacks.
Corpus scaling in RAG frequently matches the accuracy gains from larger LLMs on open-domain QA tasks, with mid-sized models benefiting most due to better passage coverage.
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
citing papers explorer
-
Averaged Evaluation Masks Capability Trade-Offs: Multi-Source Calibration for High-Sparsity LLM Pruning
At 60% SparseGPT sparsity, mixing four capability-matched calibration corpora preserves 58.8% of unpruned performance versus 40.0% for C4 — but the mix is partially calibrated on the same GSM8K and MBPP benchmarks used for evaluation.
-
Model Compression vs. Adversarial Robustness: An Empirical Study on Language Models for Code
Empirical tests show compressed code language models retain task performance but suffer markedly lower robustness under four standard adversarial attacks.
-
Less LLM, More Documents: Searching for Improved RAG
Corpus scaling in RAG frequently matches the accuracy gains from larger LLMs on open-domain QA tasks, with mid-sized models benefiting most due to better passage coverage.
-
A Survey on Efficient Inference for Large Language Models
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
-
A Survey on the Memory Mechanism of Large Language Model based Agents
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.