Research map / Large language models / Language, safety and interpretability
Ask, and Shall You Receive? Understanding Desire Fulfillment in Natural Language Text
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| normalize Desire-expression before entailment (ablation) | TE model (BIUTEE) · MCTest | F1: 34.86 -> 56.91 | Helped |
| normalize Desire-expression before entailment (ablation) | TE model (BIUTEE) · SimpleWiki | F1: 4.26 -> 14.34 | Helped |
| add latent narrative structure (LSNM) over unstructured LR | LSNM · MCTest test | F1: 66.7 -> 74.4 | Helped |
| add latent narrative structure (LSNM) over unstructured LR | LSNM · SimpleWiki test | F1: 15.2 -> 27.1 | Helped |
| analyze all evidence jointly (unstructured LR) instead of independent entailment per fragment | Unstructured LR · MCTest test | F1: 56.9 -> 66.7 | Helped |
| analyze all evidence jointly (unstructured LR) instead of independent entailment per fragment | Unstructured LR · SimpleWiki test | F1: 14.3 -> 15.2 | No clear effect |
| LSNM instead of unstructured best model in cross validation | LSNM · MCTest cross-validation | F1: 67.9 -> 70.2 | Helped |
| hand-crafted features (unstructured LR) instead of bag-of-words | Unstructured LR · MCTest test | F1: 45.2 -> 66.7 | Helped |
Closest papers by meaning
- Eliciting Human Preferences with Language Models (ICLR 2025 · similarity 0.81)
- ToMATO: Verbalizing the Mental States of Role-Playing LLMs for Benchmarking Theory of Mind (AAAI 2025 · similarity 0.80)
- Understanding the Effects of Iterative Prompting on Truthfulness (ICML 2024 · similarity 0.79)
- Interpreting Language Reward Models via Contrastive Explanations (ICLR 2025 · similarity 0.79)
- OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling (NeurIPS 2026 · similarity 0.79)
- Monitoring Latent World States in Language Models with Propositional Probes (ICLR 2025 · similarity 0.79)
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.