Ant Group: Dense retrieval's edge over BM25 in code search shrinks under fairer evaluation
CShorten30 · x · 2026-11-18
Ant Group's new paper Embeddings vs. Grep: Rethinking the Dense Advantage in Code Search finds that dense retrieval's lead over BM25 in code search shrinks considerably when evaluation is made fairer. Paper and code are publicly available, with implications for baseline selection and benchmark design in code retrieval.
More from coding & agent
- Capability Is Not Authority: The Hidden Risks of Deploying AI Agents — Adjust-the-rhythm · 2026-11-18
- SciML author shares multi-model coding workflow: role-based routing for writing and review — ChrisRackauckas · 2026-11-18
- AI Agents That Need Constant Babysitting Aren't Agents — Few-Garlic2725 · 2026-11-18
- Rebuilding the Metabase MCP Server: Lessons in MCP Tool Design — Ramirond · 2026-11-18
- Dev wants a single client to manage all agent threads with Slack-style swipe UI — curious_vii · 2026-11-18
- Adaptive UI in a Claude CLI Enterprise Assistant: Prompting Isn't Enough — Shivam__kumar · 2026-11-18