2026-11-16 ~ 11-22 · AI Search
Generative · Personalization · AI Search · Infra · Embodied AI
- 1. Too much of a good thing: Why 20 candidates beat 200 when reranking search results
Is it always better to give a reranker more candidates? Jina's team at Elastic tested its own listwise reranker on more than two dozen retrieval benchmarks, and the answer is no…
Appeared in: 11-16
- 2. RAG-FGO: Dynamic Optimization of Query-Rewriting Agents for Generative RAG · 📖 Deep dive
In retrieval-augmented generation, rewriting the user question is supposed to make retrieval more accurate, but retrieval feedback is often noisy, prompt text and decoding parameters such as temperature must be tuned…
Appeared in: 11-17
- 3. AntEmbed: Dual-Mode Multimodal Embedding Model for Efficient and Fine-Grained Retrieval · 📖 Deep dive
Multimodal retrieval has two kinds of embeddings. Discriminative embeddings encode the raw input directly, which is fast but misses fine-grained meaning. Generative embeddings first have the model reason about the…
Appeared in: 11-16
- 4. CURATOR: Scalable Fine-grained Evidence Selection for Retrieval-Augmented Generation using Decision Models · 📖 Deep dive
RAG usually stuffs whole retrieved passages into the LLM, though often only a few sentences in them can answer the question. Picking those sentences is not easy: a sentence can look irrelevant on its own…
Appeared in: 11-16
- 5. Explanations that Transfer: Interpreting Medical Retrieval with Sparse AutoEncoders · 📖 Deep dive
Medical question answering first has to retrieve relevant passages from large document collections, but the dense vectors in common use are almost impossible to explain, and fine-tuning on one corpus often loses…
Appeared in: 11-17
- 6. UMER: Unifying Embedding and Ranking via Pair-Aware Discriminative Reasoning for Universal Multimodal Retrieval
When multimodal LLMs are used for embeddings, a recent trend is to have the model write a chain of thought before encoding, injecting intermediate semantic evidence into the representation…
Appeared in: 11-16
- 7. AI-Voyager: A Public-Interest System for Human-AI Civic Reasoning to Contest and Shape the Rules That Govern AI
Governments are writing rules for artificial intelligence, often defining what counts as an automated decision or a harm before the people affected have a chance to question them…
Appeared in: 11-17
- 8. MeReader: An Offline, Privacy-Preserving, Progress-Aware AI Assistant for Narrative eBook Reading
When a language model sits beside a reader, sending the whole book in at once makes it easy to reveal later plot points, and the text often has to be uploaded to the cloud…
Appeared in: 11-17
- 9. Towards High-Performance Multimodal Discovery: Evaluating Retrieval Efficacy and Operational Scalability in Digital Libraries
In large digital libraries, many holdings are scanned pages that mix text and figures. A full-text inverted index can barely see diagrams, tables, and layout, so text from optical character recognition alone misses key…
Appeared in: 11-17
- 10. Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent
A single leaderboard score for a finance agent you did not build rarely says whether the system is stable, who should fix a failure, or whether a change can be trusted. The authors take an untuned reference agent and…
Appeared in: 11-17