Research map / Large language models / Retrieval and knowledge
Question Answering as Global Reasoning Over Semantic Abstractions
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 |
|---|---|---|---|
| Use SemanticILP instead of TupleInf | multiple-choice science QA · Regents 4th | test score (%): 67.6 vs. 61.4 | Helped |
| Use SemanticILP instead of BiDAF' | multiple-choice science QA · AI2Public 4th | test score (%): 59.7 vs. 57.4 | Helped |
| Use SemanticILP instead of IR | multiple-choice science QA · Regents 8th | test score (%): 66.0 vs. 64.2 | Helped |
| Use SemanticILP instead of IR | multiple-choice science QA · AI2Public 8th | test score (%): 55.9 vs. 52.8 | Helped |
| Use SemanticILP instead of Proread | biology reading comprehension · ProcessBank | test score (%): 67.9 vs. 68.1 | Hurt |
| Add Comb-1 (shallow alignment) (ablation) | SemanticILP · AI2Public 8th | test score: -3.1 when removed | Helped |
| Add Comb-1 (shallow alignment) (ablation) | SemanticILP · ProcessBank | test score: -1.8 when removed | Helped |
| Add Comb-2 (Verb-SRL alignment) (ablation) | SemanticILP · AI2Public 8th | test score: -2.0 when removed | Helped |
| Add Comb-2 (Verb-SRL alignment) (ablation) | SemanticILP · ProcessBank | test score: -4.6 when removed | Helped |
| Add Comb-3 (Verb-SRL and coreference alignment) (ablation) | SemanticILP · AI2Public 8th | test score: -0.6 when removed | Helped |
| Add Comb-3 (Verb-SRL and coreference alignment) (ablation) | SemanticILP · ProcessBank | test score: -1.8 when removed | Helped |
| Add Comb-4 (Verb-SRL and Comma-SRL alignment) (ablation) | SemanticILP · AI2Public 8th | test score: -3.1 when removed | Helped |
Closest papers by meaning
- Knowledge Graph Prompting for Multi-Document Question Answering (AAAI 2024 · similarity 0.88)
- Graph Reasoning Transformers for Knowledge-Aware Question Answering (AAAI 2024 · similarity 0.88)
- Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation (AAAI 2025 · similarity 0.88)
- SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs (ICLR 2024 · similarity 0.88)
- TrustUQA: A Trustful Framework for Unified Structured Data Question Answering (AAAI 2025 · similarity 0.87)
- Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models (AAAI 2025 · similarity 0.87)
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.