docs: RLM vs RAG benchmark (FinanceBench 50/50 + full)#64
Merged
Conversation
Rename rlm-benchmark.md -> rlm-vs-rag-benchmark.md; match the experiments README format; RLM vs hybrid vector RAG across both datasets with retrieval + generation metrics, time (incl. the embedding-heavy vector ingest vs RLM's lazy no-ingest), and cost; PageIndex omitted (RLM-vs-RAG view).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Reframes the benchmark doc as RLM vs hybrid vector RAG across FinanceBench 50/50 and full, matching the experiments-repo README format (RAGAS + custom + retrieval metrics, time, cost; ordered by Answer-Correctness). Shows RLM winning answer quality on both datasets (AnsCorr 0.497/0.501 vs best-RAG 0.434/0.422), the vector embedding-ingest cost (~1h16m / ~2h36m) vs RLM's lazy no-ingest, and the 50/50 production-sandbox validation (0.510, 0 failures). Renames
docs/rlm-benchmark.md→docs/rlm-vs-rag-benchmark.md. Lands in PR #43.