Research map / Label-efficient and robust learning / Recognition and long-tail
ASSESS: A Semantic and Structural Evaluation Framework for Statement Similarity
Xiaoyang Liu, Tao Zhu, Zineng Dong, Yuntian Liu, Guo qingfeng, Liu ZhaoXuan, Yu Chen, Tao Luo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add semantic-transformation (tactic) search to TED similarity (TransTED) (ablation) | TED Similarity · EPLA-miniF2F | accuracy: 69.56 -> 70.16 | Improved |
| add semantic-transformation search to TED similarity (ablation) | TED Similarity · EPLA-ProofNet | accuracy: 64.67 -> 67.31 | Improved |
| use TransTED instead of majority voting with an LLM | statement similarity · EPLA-miniF2F | Cohen's kappa: 0.14 -> 0.35 | Improved |
| use TransTED instead of proof-based BEq | statement similarity · EPLA-ProofNet | Cohen's kappa: 0.28 -> 0.30 | Improved |
| use TransTED instead of BLEU | statement similarity · EPLA-ProofNet | accuracy: 57.21 -> 67.31 | Improved |
| use TransTED instead of BEq on recall | statement similarity · EPLA-miniF2F | recall: 45.77 -> 69.06 | Improved |
| add TransTED tactic search overhead | TED Similarity · EPLA-miniF2F | average time (s): 1.2020 -> 50.5759 | Hurt |
Closest papers by meaning
- FormalAlign: Automated Alignment Evaluation for Autoformalization (ICLR 2025 · similarity 0.86)
- ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data (NeurIPS 2025 · similarity 0.86)
- Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks (ICLR 2025 · similarity 0.85)
- Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency (NeurIPS 2024 · similarity 0.85)
- Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost (NeurIPS 2025 · similarity 0.85)
- Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
