S1-MMAlign is a new large-scale dataset of 15.5 million semantically enhanced scientific image-text pairs created via an AI recaptioning pipeline to improve multimodal understanding.
hub Canonical reference
Galactica: A Large Language Model for Science
Canonical reference. 85% of citing Pith papers cite this work as background.
71
Pith papers citing it
Background
85% of classified citations
abstract
Information overload is a major obstacle to scientific progress. The explosive growth in scientific literature and data has made it ever harder to discover useful insights in a large mass of information. Today scientific knowledge is accessed through search engines, but they are unable to organize scientific knowledge alone. In this paper we introduce Galactica: a large language model that can store, combine and reason about scientific knowledge. We train on a large scientific corpus of papers, reference material, knowledge bases and many other sources. We outperform existing models on a range of scientific tasks. On technical knowledge probes such as LaTeX equations, Galactica outperforms the latest GPT-3 by 68.2% versus 49.0%. Galactica also performs well on reasoning, outperforming Chinchilla on mathematical MMLU by 41.3% to 35.7%, and PaLM 540B on MATH with a score of 20.4% versus 8.8%. It also sets a new state-of-the-art on downstream tasks such as PubMedQA and MedMCQA dev of 77.6% and 52.9%. And despite not being trained on a general corpus, Galactica outperforms BLOOM and OPT-175B on BIG-bench. We believe these results demonstrate the potential for language models as a new interface for science. We open source the model for the benefit of the scientific community.
hub tools
citation-role summary
background 11
baseline 1
method 1
citation-polarity summary
representative citing papers
BioMatrix unifies sequences, structures, and language for molecules and proteins inside one decoder-only foundation model via shared discrete tokens and achieves SOTA or competitive results on 77 of 80 downstream tasks.
SupraBench introduces four core tasks and a curated corpus to benchmark LLMs on host-guest chemistry reasoning, showing substantial remaining headroom and task-specific failure modes.
The SIU²A framework evaluates scientific images for error detection, repair feasibility, and correction quality, showing current multimodal systems have major limitations in preserving scientific validity.
OOD-GraphLLM is a graphLLM framework that jointly optimizes molecular graph representations and biomedical semantic language representations for out-of-distribution drug synergy prediction.
The work creates a new ground truth dataset for mapping queries to verbatim text spans in research papers and shows a 150M-parameter ModernBERT token classifier achieving 53.6 word-level F1, outperforming LLM extractors at 48.7.
PPI2Text generates natural-language captions for protein-protein interactions from sequences by encoding each protein with ESM3, building a residue-pair map, and decoding with Qwen3 using coordinate-aligned positional encoding.
An interactive AI workbench for mathematicians achieves 48% on FrontierMath Tier 4 and helped solve open problems in early tests.
AstroAlertBench evaluates multimodal LLMs on astronomical classification accuracy, reasoning, and honesty using real ZTF alerts, revealing that high accuracy often diverges from self-assessed reasoning quality.
Small 7B reasoning models were fine-tuned on synthetic and curated QFT problems using RL and SFT, yielding performance gains, error analysis, and public release of data and traces.
LLMs predict outcomes of real scientific experiments at 14-26% accuracy, comparable to human experts, but lack calibration on prediction reliability while humans demonstrate strong calibration.
FactReview extracts claims from ML papers, positions them via literature retrieval, and verifies them through code execution, labeling each as Supported, Partially supported, or In conflict, as shown in a CompGCN case study.
Stronger LLMs show near-perfect physical reasoning in circuits but violate explicit sign and polarity instructions in trap setups, while weaker models follow instructions better but reason less accurately.
S^2-Bench is a new one-to-many benchmark for natural language-driven molecule generation with three tasks, and OpenMolIns is an instruction dataset enabling Llama3.1-8B to outperform GPT-4o and Claude-3.5 on it.
PolyMATH is a new 5,000-image benchmark where top MLLMs reach at most 41 percent accuracy on multi-modal mathematical reasoning, with ablation showing minimal gain from text over images.
Active-GRPO reaches 0.1773 average SRxSim on TOMG-Bench MOLOPT by adaptively switching between imitation and self-reinforcement while upgrading references, outperforming GRPO and RePO.
DrugClaw tops benchmarks on primary-source grounding and faithfulness for drug-information QA while DrugAudit provides an authority-aware evaluation set of 3,772 items.
Evaluation of 6233 MedGPTs finds 25-30% with low factual accuracy, 33.6-54.3% violating operational thresholds, and 57% of action-enabled models lacking privacy disclosures.
DEL is a new loss for LLM numerical learning that applies supervised digit entropy optimization and extends to floating-point numbers, showing improved accuracy and distance metrics over prior methods on math benchmarks.
2D-ProteinRAG is a dual-dimensional RAG framework that incorporates BLAST workflows plus horizontal attribute alignment and vertical homology denoising to improve protein-text QA on both in-distribution and out-of-distribution cases.
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
Malicious actors could use AI agents to submit large numbers of fake papers, inflating the submission count and thereby raising the acceptance odds for a small set of chosen legitimate papers under stable conference acceptance rates.
FAME models scientific topic trajectories in continuous time to forecast paper impact more accurately than LLMs by aligning manuscripts with field momentum in a dynamic latent space.
SPARK constructs unified knowledge graphs from multi-document scientific literature to ground self-play RL with asymmetric roles and verifiable rewards, outperforming flat-corpus baselines especially on longer-hop reasoning tasks.
citing papers explorer
-
DEL: Digit Entropy Loss for Numerical Learning of Large Language Models
DEL is a new loss for LLM numerical learning that applies supervised digit entropy optimization and extends to floating-point numbers, showing improved accuracy and distance metrics over prior methods on math benchmarks.
-
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
KIVI applies asymmetric 2-bit quantization to KV cache with per-channel keys and per-token values, reducing memory 2.6x and boosting throughput up to 3.47x with near-identical quality on Llama, Falcon, and Mistral.
-
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
Bootstrapping math questions via rewriting creates MetaMathQA; fine-tuning LLaMA-2 on it yields 66.4% on GSM8K for 7B and 82.3% for 70B, beating prior same-size models by large margins.
-
MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning
MAmmoTH models trained via hybrid CoT-PoT instruction tuning on MathInstruct outperform prior open-source LLMs by 16-32% average accuracy on nine math datasets, reaching 33% and 44% on MATH for 7B and 34B scales.
-
Scaling Data-Constrained Language Models
Repeating training data up to 4 epochs yields negligible loss increase versus unique data for fixed compute, and a new scaling law accounts for the decaying value of repeated tokens and excess parameters.