AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

DeFuzzRAG: Handling Fuzzy Time Expressions for Temporal Robustness in Retrieval-Augmented Generation

Ling-Chun Chen, Hsi-Wen Chen, Ming-Syan Chen

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add temporal intent extraction, metadata inference and overlap filtering after dense retrievalMPNet retriever · TempFuzz-QA fuzzy queriesHit Rate: 0.6712 -> 0.7765 (LLaMA2-7B parser)Improved
fuzzify temporal expressions in documents and queriesMPNet, BM25, BGE retrievers · TempFuzz-QAHit Rate: MPNet 0.7908 -> 0.6712; BM25 0.5574 -> 0.4587Hurt
fuzzify documents (temporal expressions made vague)retriever attention · 1,000 query-document pairsTime Attention Ratio: 27.7% average dropHurt
use a 7B parser (Mistral-7B) instead of GPT-4 for temporal parsing (ablation)DeFuzzRAG · TempFuzz-QA fuzzyMRR: 0.5483 -> 0.5402, latency 11.14 s -> 2.84 sNo clear effect
use TinyLLaMA-1.1B as temporal parser instead of 7B models (ablation)DeFuzzRAG · TempFuzz-QA fuzzyMRR: 0.5402 -> 0.4702 (vs Mistral-7B)Hurt
add DeFuzzRAG on explicit (clean) queriesMPNet retriever · TempFuzz-QA explicitHit Rate: 0.7908 -> 0.8125Improved
add DeFuzzRAG to spatially fuzzified queriesMPNet retriever · SpaceFuzz-QAHit Rate: 0.7253 -> 0.7834Improved
use fuzzy type Generalized Dating instead of other fuzziness types (ablation)DeFuzzRAG · TempFuzz-QA by fuzziness typeHit Rate (fuzzy): GD lowest, about 0.57Hurt
query type with strong temporal anchors (Event-Anchored, Year-Specific) vs range queries (ablation)DeFuzzRAG · TempFuzz-QA by query typeHit Rate (fuzzy): ET about 0.90, YS about 0.87Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy