MARD-7B outperforms baselines and GPT-4o on novel drug pairs for mechanism-level DDI prediction via a new distillation pipeline with verifiable process rewards and releases all resources.
Common 7b language models already possess strong math capabilities
6 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
6
Pith papers citing it
3
external citations · external index
representative citing papers
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.
A curated set of one billion personas enables scalable, diverse synthetic data generation for LLM training across reasoning, instructions, knowledge, NPCs, and tools.
Step-DPO performs preference optimization on individual reasoning steps rather than complete answers, producing nearly 3% accuracy gains on MATH for 70B+ parameter models with 10K preference pairs.
FedProxy replaces weak adapters with a proxy SLM for federated LLM fine-tuning, outperforming prior methods and approaching centralized performance via compression, heterogeneity-aware aggregation, and training-free fusion.
A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.
citing papers explorer
-
MARD: Mirror-Augmented Reasoning Distillation for Mechanism-Level Drug-Drug Interaction Prediction
MARD-7B outperforms baselines and GPT-4o on novel drug pairs for mechanism-level DDI prediction via a new distillation pipeline with verifiable process rewards and releases all resources.
-
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.
-
Scaling Synthetic Data Creation with 1,000,000,000 Personas
A curated set of one billion personas enables scalable, diverse synthetic data generation for LLM training across reasoning, instructions, knowledge, NPCs, and tools.
-
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
Step-DPO performs preference optimization on individual reasoning steps rather than complete answers, producing nearly 3% accuracy gains on MATH for 70B+ parameter models with 10K preference pairs.
-
FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion
FedProxy replaces weak adapters with a proxy SLM for federated LLM fine-tuning, outperforming prior methods and approaching centralized performance via compression, heterogeneity-aware aggregation, and training-free fusion.
-
The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes
A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.