Research map / Large language models / Language, safety and interpretability
Mitigating Reporting Bias in Semi-supervised Temporal Commonsense Inference with Probabilistic Soft Logic
Bibo Cai, Xiao Ding, Bowen Chen, Li Du, Ting Liu
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 PSL soft-logic regularization | BERT-based SLEER · TimeML-tr | distance: 1.61 -> 1.39 | Improved |
| Add PSL soft-logic regularization | BERT-based SLEER · MCTACO-freq | distance: 1.28 -> 1.06 | Improved |
| Add PSL soft-logic regularization | BERT-based SLEER · RealNews | distance: Duration 0.75 -> 0.75; Frequency 1.17 -> 1.03; Day 1.72 -> 1.61; Week 1.19 -> 1.08; Month 3.42 -> 3.17; Season 0.63 -> 0 | Mixed |
| Add PSL soft-logic regularization | BERT-based SLEER · UDS-T duration | distance: 1.49 -> 1.55 | Hurt |
| Add PSL soft-logic regularization | RoBERTa-based SLEER · TimeML | accuracy: 81.1 -> 83.8 | Improved |
| Add PSL soft-logic regularization | RoBERTa-based SLEER · MCTACO | EM: 41.3 -> 43.0 | Improved |
| Add PSL soft-logic regularization | RoBERTa-based SLEER · MCTACO | F1: 67.3 -> 69.0 | Improved |
| Add complementary temporal-dimension logic as hard-rule data augmentation (ablation) | BASE · TimeML-tr | distance: 1.80 -> 1.52 | Improved |
| Add complementary temporal-dimension logic as hard-rule data augmentation (ablation) | BASE · MCTACO-freq | distance: 1.10 -> 1.09 | Improved |
| Replace hard-rule augmentation with soft PSL regularization (ablation) | BASE+Hard Rule · TimeML-tr | distance: 1.52 -> 1.39 | Improved |
| Replace hard-rule augmentation with soft PSL regularization (ablation) | BASE+Hard Rule · MCTACO-freq | distance: 1.09 -> 1.06 | Improved |
Closest papers by meaning
- Self-Supervised Logic Induction for Explainable Fuzzy Temporal Commonsense Reasoning (AAAI 2023 · similarity 0.88)
- Latent Logic Tree Extraction for Event Sequence Explanation from LLMs (ICML 2024 · similarity 0.83)
- COLD: Causal reasOning in cLosed Daily activities (NeurIPS 2024 · similarity 0.83)
- NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language Models (AAAI 2026 · similarity 0.83)
- Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space (NeurIPS 2025 · similarity 0.82)
- TimE: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios (NeurIPS 2025 · similarity 0.82)
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.
