LAB-Bench provides over 2,400 multiple-choice questions to measure LLM performance on real biology research tasks like literature recall, figure reading, database access, and sequence manipulation, with initial results compared against human expert biologists.
Measuring massive multitask language understanding
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
WE-MATH benchmark reveals most LMMs rely on rote memorization for visual math while GPT-4o has shifted toward knowledge generalization.
LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.
STS repurposes draft-model attention scores from speculative decoding to build token-and-head-wise sparsity masks, delivering 2.67x speedup at ~90% sparsity on NarrativeQA with negligible accuracy loss.
FineWeb is a curated 15T-token web dataset that produces stronger LLMs than prior open collections, while its educational subset sharply improves performance on MMLU and ARC benchmarks.
Zephyr-7B achieves state-of-the-art chat benchmark results among 7B models by distilling alignment via dDPO on AI feedback preferences, surpassing the 70B Llama-2-Chat model on MT-Bench with no human data required.
STELLA aligns ESM3 bimodal sequence-structure encodings with Llama-3.1-8B text modeling to claim state-of-the-art results on protein functional description prediction and enzyme-catalyzed reaction prediction.
citing papers explorer
-
LAB-Bench: Measuring Capabilities of Language Models for Biology Research
LAB-Bench provides over 2,400 multiple-choice questions to measure LLM performance on real biology research tasks like literature recall, figure reading, database access, and sequence manipulation, with initial results compared against human expert biologists.
-
We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?
WE-MATH benchmark reveals most LMMs rely on rote memorization for visual math while GPT-4o has shifted toward knowledge generalization.
-
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.
-
STS: Efficient Sparse Attention with Speculative Token Sparsity
STS repurposes draft-model attention scores from speculative decoding to build token-and-head-wise sparsity masks, delivering 2.67x speedup at ~90% sparsity on NarrativeQA with negligible accuracy loss.
-
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
FineWeb is a curated 15T-token web dataset that produces stronger LLMs than prior open collections, while its educational subset sharply improves performance on MMLU and ARC benchmarks.
-
Zephyr: Direct Distillation of LM Alignment
Zephyr-7B achieves state-of-the-art chat benchmark results among 7B models by distilling alignment via dDPO on AI feedback preferences, surpassing the 70B Llama-2-Chat model on MT-Bench with no human data required.
-
STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding
STELLA aligns ESM3 bimodal sequence-structure encodings with Llama-3.1-8B text modeling to claim state-of-the-art results on protein functional description prediction and enzyme-catalyzed reaction prediction.