Research map / Large language models / Language, safety and interpretability
Self-Supervised Logic Induction for Explainable Fuzzy Temporal Commonsense Reasoning
Bibo Cai, Xiao Ding, Zhouhao Sun, Bing Qin, Ting Liu, Baojun wang, Lifeng Shang
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 LECTER temporal logic induction and defuzzification to RoBERTa-base | RoBERTa-base · TIMEDIAL test | 2-best accuracy: 59.3 -> 71.5 | Improved |
| Add LECTER temporal logic induction and defuzzification to BERT-base | BERT-base · TIMEDIAL test | 2-best accuracy: 53.7 -> 65.8 | Improved |
| Continually pre-train RoBERTa-base with temporal-aware objectives rather than evaluate zero-shot | RoBERTa-base · TIMEDIAL test | 2-best accuracy: 52.2 -> 59.3 | Improved |
| Continually pre-train BERT-base with temporal-aware objectives rather than evaluate zero-shot | BERT-base · TIMEDIAL test | 2-best accuracy: 44.8 -> 53.7 | Improved |
| Add temporal value regression (ablation) | LECTER with RoBERTa-base · TIMEDIAL test | 2-best accuracy: 62.5 -> 71.5; 9.0% | Improved |
| Add temporal logic induction (ablation) | LECTER with RoBERTa-base · TIMEDIAL test | 2-best accuracy: 69.4 -> 71.5; 2.1% | Improved |
Closest papers by meaning
- NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language Models (AAAI 2026 · similarity 0.88)
- TimE: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios (NeurIPS 2025 · similarity 0.88)
- Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning (ICLR 2025 · similarity 0.86)
- ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos (NeurIPS 2024 · similarity 0.84)
- COLD: Causal reasOning in cLosed Daily activities (NeurIPS 2024 · similarity 0.84)
- Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning (NeurIPS 2024 · similarity 0.84)
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.
