2026-11-09 ~ 11-15 · AI Search
Generative · Personalization · AI Search · Infra · Embodied AI
- 1. Beyond Ranking: Are Decision Models Calibrated Relevance Scorers? · 📖 Deep dive
Decision models such as Jev generate no text and output a probability for each relevance level directly, and the vendor promises those probabilities are calibrated, yet earlier independent checks never compared them…
Appeared in: 11-11
- 2. Yuanbao-Reranker: Document-Grounded Synthesis and Preference Distillation for Text Reranking · 📖 Deep dive
Rerankers fine-tuned pointwise on relevant and not-relevant labels have a gap: every negative for a query carries the same label, so the model never learns which negatives sit closer to the positive…
Appeared in: 11-11
- 3. Lightfoot: Graph Retrieval-Augmented Generation with Exact, Model-Free Document Deletion · 📖 Deep dive
GraphRAG in production has two costs that papers rarely count: what it takes to build the graph, and how painful it is to delete a document. When a contract expires or a user asks for erasure…
Appeared in: 11-11
- 4. Beyond Query-Item Matching: Personalized Behavioral Relevance Modeling for E-commerce Search via Rubric-Guided Reinforcement Learning · 📖 Deep dive
E-commerce search usually has a relevance model sort candidates into tiers by text match between query and item, then hands them to a CTR model, so an item the user clearly prefers can get little exposure just because…
Appeared in: 11-13
- 5. SPARSEUP: Towards Better Recipes for Training Modern Learned Sparse Retrievers
Sparse retrievers like SPLADE, moved onto newer backbones such as ModernBERT, often train poorly, and RoBERTa does not train at all. The authors trace this to the starting point: most of the new backbones' vocabulary…
Appeared in: 11-10
- 6. Calibrating Document-Local Boundaries for Contextual Chunk Retrieval
Late Chunking encodes a whole document before splitting it, which preserves context but makes similar chunks of the same document harder to tell apart, such as one player's scoring records from different seasons…
Appeared in: 11-11
- 7. CoRA-Bench: Evaluating Evidence Preservation by Context Selectors Under Token Budgets
Filtering content before long-context inference saves tokens, but it can also throw away the evidence the answer needs, and truncation, retrieval and compression have lacked a common way to be compared…
Appeared in: 11-11
- 8. NIFT-SQL: Customer-Supervised Table Scoring for Enterprise Text-to-SQL Retrieval
The first step of enterprise text-to-SQL is finding the tables, yet schemas often offer only cryptic table and column names, a query needs every table it joins, and generic retrieval struggles here…
Appeared in: 11-11
- 9. PatternBloom: Empowering Agentic RAG with Externalized RL-Distilled Graph Patterns
RAG agents trained with reinforcement learning can learn to fetch better content, yet the steps for reasoning through a given type of question are worked out from scratch every time…
Appeared in: 11-11
- 10. Search-by-Answer Bias in Retrieval Models
Dense retrieval should find passages by the relation a query asks about, but retrieval models carry world knowledge, and this paper shows they lean toward answers the model already knows…
Appeared in: 11-11