Dwarakesh Baraneetharan

Computer Science  ·  Mathematics

Loading000
Skip to content
All work
02 / Evaluated RAG engine2026

A claim verification system over scientific abstracts that enforces grounded citations and gates CI on retrieval quality.

0.94
nDCG@5
0.88
Recall@5
100%
grounded citations
Author
my role

Overview

Stack

  • Python
  • FastAPI
  • SciFact
  • SentenceTransformers

LLMs hallucinate, especially on scientific literature. Warrant addresses this by grounding generations in retrieved evidence from the SciFact corpus. More importantly, it treats retrieval as an engineering problem: the pipeline uses a hybrid BM25 and dense embedding search with Reciprocal Rank Fusion (RRF), re-ranked by a domain-specific biomedical cross-encoder. The CI pipeline fails if retrieval metrics (nDCG, Recall) regress against human judgments.

What I did

  1. 01Implemented a hybrid retrieval pipeline using BM25, SentenceTransformers, and a MedCPT cross-encoder.
  2. 02Built a rigorous evaluation harness that scores retrieval against the human-annotated SciFact benchmark.
  3. 03Configured GitHub Actions to gate pull requests on retrieval quality regressions (nDCG@5, Recall@5).
  4. 04Enforced strict citation constraints on the LLM generation step to ensure all claims are verifiable.
Next project

CapitalBikeRoute+

Constrained micromobility routing