Research map / Large language models / Retrieval and knowledge
Text Assisted Insight Ranking Using Context-Aware Memory Network
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 |
|---|---|---|---|
| add header semantics to the insight representation (ablation) | TAR_cnn · Financial Report Dataset | Precision@1: 0.118 -> 0.162 | Helped |
| add table-context memory over related insights (ablation) | TAR_semantics · Financial Report Dataset | Precision@1: 0.162 -> 0.170 | Helped |
| add subspace CNN features to significance and insight-type features (ablation) | TAR · Financial Report Dataset | Precision@1: 0.110 -> 0.118 | Helped |
| cluster subspaces using header embeddings before calculating significance | Sig_cluster · Financial Report Dataset | Precision@1: 0.098 -> 0.110 | Helped |
| calculate significance across all dataset tables rather than within one table | Significance scoring · Financial Report Dataset | Precision@1: 0.098 -> 0.107 | Helped |
| use text similarity that also weights header matches | Text assistance similarity function · Financial report insight-sentence matching | Accuracy | Helped |
| add table-context memory over related insights (ablation) | TAR_semantics · SBNation Dataset | Precision@1: 0.788 -> 0.797 | Helped |
Closest papers by meaning
- Scalable In-context Ranking with Generative Models (NeurIPS 2025 · similarity 0.81)
- TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking (AAAI 2026 · similarity 0.81)
- Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers (ICLR 2025 · similarity 0.81)
- SiReRAG: Indexing Similar and Related Information for Multihop Reasoning (ICLR 2025 · similarity 0.80)
- InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation (ICLR 2025 · similarity 0.80)
- KnowPO: Knowledge-Aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Models (AAAI 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.