Research map / Vision-language and multimodal / Visual question answering
Fact Checking in Community Forums
Tsvetomila Mihaylova, Preslav Nakov, Lluís Màrquez, Alberto Barrón-Cedeño, Mitra Mohtarami, Georgi Karadzhov, James Glass
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 |
|---|---|---|---|
| Combine the multi-faceted feature groups and optimize for MAP | Fact Checking in Community Forums · CQA-QL-2016-fact | MAP: 86.54; 23 points of improvement over the chronological baseline, absolute | Improved |
| Combine the multi-faceted feature groups and optimize for accuracy | Fact Checking in Community Forums · CQA-QL-2016-fact | accuracy: 72.29; 19 points of improvement over the majority class baseline, absolute | Improved |
| Use Qatar Living-wide answer support | Fact Checking in Community Forums · CQA-QL-2016-fact | MAP: 83.97 | Improved |
| Use general Google News embeddings instead of domain-trained embeddings | Fact Checking in Community Forums · CQA-QL-2016-fact | accuracy: 59.44 -> 52.61 | Hurt |
| Use user activity features alone | Fact Checking in Community Forums · CQA-QL-2016-fact | accuracy: 42.57 vs. 51.41 | Hurt |
| Remove query generation and use the entire answer for evidence retrieval (ablation) | High-quality posts in Qatar Living · CQA-QL-2016-fact | accuracy: 12 accuracy points | Hurt |
| Remove query generation and use the entire answer for evidence retrieval (ablation) | High-quality posts in Qatar Living · CQA-QL-2016-fact | accuracy: 4 accuracy points | Hurt |
| Remove entailment-based re-ranking (ablation) | High-quality posts in Qatar Living · CQA-QL-2016-fact | accuracy: 11 accuracy points | Hurt |
| Remove entailment-based re-ranking (ablation) | High-quality posts in Qatar Living · CQA-QL-2016-fact | accuracy: 3 accuracy points | Hurt |
Closest papers by meaning
- Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking (NeurIPS 2025 · similarity 0.80)
- What Is a Good Question? Assessing Question Quality via Meta-Fact Checking (AAAI 2025 · similarity 0.80)
- TrustUQA: A Trustful Framework for Unified Structured Data Question Answering (AAAI 2025 · similarity 0.79)
- Is Complex Query Answering Really Complex? (ICML 2025 · similarity 0.79)
- CofCA: A STEP-WISE Counterfactual Multi-hop QA benchmark (ICLR 2025 · similarity 0.79)
- RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content (NeurIPS 2024 · 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.
