Why memorizing for the exam doesn't mean you understand the subject The post Water Cooler Small Talk, Ep. 11: Overfitting in RAG evaluation appeared first on Towards Data Science .
Two techniques, two different problems, and why the question is not really "which one wins" The post RAG vs Fine-Tuning Explained: What They Actually Do and When to Use Each appeared first on Towards Data Science .
A tiny GPT model was trained to memorize every fact presented to it, yet it failed to answer any question that required combining two of those facts. The author tested a one-line fix suggested in a recent paper, which only partially resolved the issue. The post highlights the limitations of small language models in integrating multiple pieces of information.
Enterprise Document Intelligence [Vol. 1 #4bis] - A coauthor note on the brick-by-brick pitfalls that justified the four-brick split, before Part II walks the fixes The post 10 Common RAG Mistakes We Keep Seeing in Production appeared first on Towards Data Science .
The article titled "10 Positions for Enterprise RAG That Mainstream Tutorials Get Wrong" discusses ten key positions related to Enterprise Document Intelligence, as outlined in the series "Enterprise Document Intelligence [Vol.1 #M3]. It also provides a map of every article that supports these positions.
Enterprise Document Intelligence [Vol. 1 #6bis] - Ask one focused clarification, learn the default from the answer, stay silent next time The post When RAG Users Ask Vague Questions: Clarify Once, Learn the Default appeared first on Towards Data Science .
The study examined how undergraduate English learners perceive feedback from large language models that incorporate process-aware data such as intermediate drafts and keystroke records. Forty‑three participants completed a timed essay, received LLM‑generated feedback based on the final draft, intermediate snapshots, and interaction logs, and then rated the feedback on six Likert items and answered open‑ended questions. Ratings were largely positive, with 74.4%–95.3% of participants giving 4 or 5 stars, and qualitative analysis revealed that most learners found the feedback accurate, though some noted misinterpretations or time constraints.
Enterprise Document Intelligence [Vol. 1 #7ter] - Six positions on the retrieval brick that contradict the cosine-first reflex of mainstream RAG The post The Untaught Lessons of RAG Retrieval: Cosine Is Not the Foundation appeared first on Towards Data Science .
Enterprise Document Intelligence [Vol. 1 #6quinquies] - Prompt engineering, then context engineering, then loop engineering.
Cross-provider PR review with Codex in GitHub Actions, and why a second opinion from a different lab beats any self-review The post Don’t Let Claude Grade Its Own Homework appeared first on Towards Data Science .
I built four AI retrieval architectures on a laptop and benchmarked them against the same set of documents and questions. Here’s what the results taught me about the trade-offs between plain RAG, grap...
The downside of conference travel The post Last Month’s Machine Learning Lessons Learned appeared first on Towards Data Science .
The paper proposes using large language models (LLMs) to identify disagreements among models as a way to focus expert effort on revising codebooks for large‑scale text annotation. Three expert feedback methods are evaluated: editing LLM‑generated revisions (Codebook Verifying), answering questions about disagreements (Question Answering), and labeling disagreement cases with rationales (Rationale Labeling). Experiments on tutoring‑session transcripts show that Rationale Labeling achieves the highest LLM‑labeling accuracy (64.9%) compared to the expert‑revised codebook (57.8%), with Question Answering also outperforming the baseline (60.5%).