Papers › Entity-Conditioned Question Generation for Robust Attention Distribution in Neural...

Entity-Conditioned Question Generation for Robust Attention Distribution in Neural Information Retrieval

24 Apr 2022arXiv:2204.11373archive 2025-07-28

Revanth Gangi Reddy, Md Arafat Sultan, Martin Franz, Avirup Sil, Heng Ji

We show that supervised neural information retrieval (IR) models are prone to learning sparse attention patterns over passage tokens, which can result in key phrases including named entities receiving low attention weights, eventually leading to model under-performance. Using a novel targeted synthetic data generation method that identifies poorly attended entities and conditions the generation episodes on those, we teach neural IR to attend more uniformly and robustly to all entities in a given passage. On two public IR benchmarks, we empirically show that the proposed method helps improve both the model's attention patterns and retrieval performance, including in zero-shot settings.

PaperPDFCode

Code

blender-nlp/entityconditionedqgen officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Information RetrievalQuestion GenerationQuestion-GenerationRetrievalSynthetic Data Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections