KrishokChat: A Provenance-Traceable Multi-Task Bengali Agricultural Benchmark with Safety-Critical Chemical Advisory
We introduce KrishokChat, an 85,979-instance Bengali agricultural benchmark built from 284 government publications, 13 institutions, and six regional dialects. The benchmark comprises four tracks: General Knowledge QA, Treatment QA, Safety Refusal and Re-query, and Table QA. It also includes a 1,000-query Real-World Farmer Benchmark collected independently from field interviews to measure transfer to authentic farmer language. Every extracted instance retains provenance at the citation level. Treatment QA also provides a structured chemical-trace array for dosage-level auditability. We evaluated five zero-shot baselines and one fine-tuned model. Closed-book knowledge proves insufficient r...
| Authors | Khan Raiyan Ibne Reza, Sumaiya Tabassum Nimi, Omar Ibne Shahid |
|---|---|
| Primary category | cs.LG |
| Published | 28 June 2026 |
| Last updated at source | 10 August 2026 |
Connected in the knowledge graph
- RaiyanKhaan/KrishokChatDataset · cited by
Models and datasets referencing this paper
- RaiyanKhaan/KrishokChatDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.