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.
58
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
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.
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.
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.
K-MetBench shows LLMs have large gaps in interpreting meteorology diagrams and Korean-specific context, with smaller local models beating much larger global ones.
QuantumQA dataset and verification-aware RL with adaptive reward fusion enable an 8B LLM to achieve performance competitive with proprietary models on quantum mechanics tasks.
MolDA is a multimodal molecular model that uses a discrete large language diffusion backbone plus a hybrid graph encoder to achieve better global coherence and validity than autoregressive approaches.
CAMEL is a scaling law capturing nonlinear model-size and mixture interactions to extrapolate optimal data mixtures for large LLMs from small-model experiments, reducing optimization cost by 50% and improving benchmarks by up to 3%.
A modified divergence decouples top-K teacher probabilities from the distribution tail during distillation, yielding competitive performance on decoder models with standard compute.
MOSAIC is a training-free multi-agent LLM framework with rationale, coding, reflection, and debugging agents plus a consolidated context window that outperforms prior methods on scientific coding benchmarks.
citing papers explorer
-
S1-MMAlign: A Large-Scale, Multi-Disciplinary Dataset for Scientific Figure-Text Understanding
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.
-
OOD-GraphLLM: Graph Large Language Model for Out-of-Distribution Generalized Drug Synergy Prediction
OOD-GraphLLM is a graphLLM framework that jointly optimizes molecular graph representations and biomedical semantic language representations for out-of-distribution drug synergy prediction.
-
ACL-Verbatim: hallucination-free question answering for research
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: Captioning Protein-Protein Interactions with Coordinate-Aligned Pair-Map Decoding
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.
-
AI co-mathematician: Accelerating mathematicians with agentic AI
An interactive AI workbench for mathematicians achieves 48% on FrontierMath Tier 4 and helped solve open problems in early tests.
-
AstroAlertBench: Evaluating the Accuracy, Reasoning, and Honesty of Multimodal LLMs in Astronomical Classification
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.
-
Fine-Tuning Small Reasoning Models for Quantum Field Theory
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.
-
SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?
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: Evidence-Grounded Reviews with Literature Positioning and Execution-Based Claim Verification
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.
-
CircuChain: Disentangling Competence and Compliance in LLM Circuit Analysis
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.
-
Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models
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: 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.
-
Unlocking Biological Workflows for Robust Protein-Text Question Answering: A Dual-Dimensional RAG Framework
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.
-
Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents
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: Forecasting Academic Impact via Continuous-Time Manifold Evolution
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: Self-Play with Asymmetric Reward from Knowledge Graphs
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.
-
K-MetBench: A Multi-Dimensional Benchmark for Fine-Grained Evaluation of Expert Reasoning, Locality, and Multimodality in Meteorology
K-MetBench shows LLMs have large gaps in interpreting meteorology diagrams and Korean-specific context, with smaller local models beating much larger global ones.
-
QuantumQA: Enhancing Scientific Reasoning via Physics-Consistent Dataset and Verification-Aware Reinforcement Learning
QuantumQA dataset and verification-aware RL with adaptive reward fusion enable an 8B LLM to achieve performance competitive with proprietary models on quantum mechanics tasks.
-
MolDA: Molecular Understanding and Generation via Large Language Diffusion Model
MolDA is a multimodal molecular model that uses a discrete large language diffusion backbone plus a hybrid graph encoder to achieve better global coherence and validity than autoregressive approaches.
-
Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization
CAMEL is a scaling law capturing nonlinear model-size and mixture interactions to extrapolate optimal data mixtures for large LLMs from small-model experiments, reducing optimization cost by 50% and improving benchmarks by up to 3%.
-
Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation
A modified divergence decouples top-K teacher probabilities from the distribution tail during distillation, yielding competitive performance on decoder models with standard compute.
-
SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules
SciCore-Mol augments LLMs with three integrated modules for molecular perception, latent diffusion generation, and reaction reasoning, claiming an 8B open model competes with or exceeds proprietary systems on chemical tasks.
-
RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems
RUBEN discovers minimal rule sets explaining RAG LLM outputs via novel pruning and applies them to evaluate LLM safety against adversarial injections.
-
Scale-Dependent Input Representation and Confidence Estimation for LLMs in Materials Property Prediction
Larger LLMs handle detailed crystal descriptions better than small ones, and mean negative log-likelihood of predicted numbers tracks prediction error after fine-tuning.
-
Bolek: A Multimodal Language Model for Molecular Reasoning
Bolek injects Morgan fingerprint embeddings into an instruction-tuned text model, then fine-tunes on molecular alignment and synthetic chain-of-thought tasks to improve performance and grounding on 15 TDC binary classification endpoints while generalizing to unseen tasks.
-
Heterogeneous Scientific Foundation Model Collaboration
Eywa enables language-based agentic AI systems to collaborate with specialized scientific foundation models for improved performance on structured data tasks.
-
From Perception to Autonomous Computational Modeling: A Multi-Agent Approach
A multi-agent LLM framework autonomously completes the full computational mechanics pipeline from a photograph to a code-compliant engineering report on a steel L-bracket example.
-
Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs
A data-driven adaptive policy for KV-cache bit-width selection based on token importance features reduces decoding latency by ~18% and improves accuracy over static quantization while staying near FP16 levels on SmolLM models.
-
Do We Need Bigger Models for Science? Task-Aware Retrieval with Small Language Models
Task-aware retrieval with small models partially compensates for reduced scale in scholarly QA but model capacity remains important for complex reasoning.
-
Heterogeneous Graph Importance Scoring and Clustering with Automated LLM-based Interpretation
An open-data pipeline constructs heterogeneous graphs from OSM, computes five social impact scores per bridge, applies UMAP+HDBSCAN clustering to find archetypes, and uses domain-tuned LLMs to generate policy interpretations.
-
Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages
A tutorial synthesizing foundations, recent models such as PALO and Maya, and low-cost methods for tri-modal multilingual AI in resource-constrained settings.
- REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations