SA-Bench: Evaluating Semantic Alignment in LLM-Based Paper Reproduction
cs.AI, cs.SE
Submitted: 2026-08-25
Updated: 2026-08-25
Code: https://github.com/kernel-14/SemanticAlign-BenchData:https:
Terminology
Sources
- Program Synthesis with Large Language Models
- SciCoQA: Quality Assurance for Scientific Paper--Code Alignment
- Evaluating Large Language Models Trained on Code
- NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
- SedarEval: Automated Evaluation using Self-Adaptive Rubrics
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge
- Enhancing Automated Paper Reproduction via Prompt-Free Collaborative Agents
- AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers
- RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
- S2ORC: The Semantic Scholar Open Research Corpus
- GPT-4o System Card
- SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
- PRBench: End-to-end Paper Reproduction in Physics Research
- CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark
- PaperBench: Evaluating AI's Ability to Replicate AI Research
- SciCode: A Research Coding Benchmark Curated by Scientists
- CodeJudge: Evaluating Code Generation with Large Language Models
- MinerU: An Open-Source Solution for Precise Document Content Extraction
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection