Topic - Edition
Two BM25 optimizations and benchmark configuration changes inspired by PlanetScale's TIN benchmarks make ParadeDB's text search faster without changing its document identifiers.
I am currently working on an open-source web app store project. It utilizes a hybrid architecture: a fast server-side rendering (SSR) engine that is subsequently taken over by a lightweight JavaScript program on the…
arXiv:2609.38397v1 Announce Type: new Abstract: Virtual clients offer a cost-effective approach to support applications such as A/B testing, recommender system development, and interface evaluation. However, building…
arXiv:2609.36326v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) hands the user's query to whoever hosts the corpus. We propose PILLAR, a Privacy-Preserving RAG (PPRAG) system based on Private…
arXiv:2609.39007v1 Announce Type: new Abstract: Sessionized interaction histories contain behavioral patterns that can improve sequential recommendation. However, existing models process all sessions through the same…
arXiv:2609.38639v1 Announce Type: cross Abstract: LLM-guided evolutionary search can discover complex programs, but existing methods mostly only save candidate programs and fitness scores while discarding which…
arXiv:2605.29307v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) search agents have shown strong promise on knowledge-intensive tasks through iterative reasoning and retrieval. Most existing systems…
arXiv:2609.39975v1 Announce Type: cross Abstract: This paper presents an overview of the fourteenth edition of the BioASQ challenge, organized in the context of the Conference and Labs of the Evaluation Forum (CLEF)…
arXiv:2609.39013v1 Announce Type: cross Abstract: EVICALC, our system for the DocSem shared task, achieved 8.61% joint accuracy on 1,730 tasks in the official final test evaluation. It reads a PDF, selects a passage,…
arXiv:2609.38646v1 Announce Type: new Abstract: Generative recommendation (GR) has emerged as an alternative to embedding-based retrieval, building on the success of generative models in language and vision. We are…
arXiv:2609.38289v1 Announce Type: cross Abstract: In personalized AI applications, such as conversational assistants and recommender systems, users interact not with models in isolation but with broader systems that…
arXiv:2609.39043v1 Announce Type: new Abstract: Large language models (LLMs) enable rich semantic user profiles for recommendation, but such profiles are more expensive to generate and are not necessarily desirable to…
arXiv:2609.40241v1 Announce Type: new Abstract: Large language models (LLMs) have shown promise for recommendation reranking, but their use introduces an important tradeoff between recommendation quality and serving…
arXiv:2609.37183v2 Announce Type: replace Abstract: Industrial recommendation ranking models typically scale along two modeling axes: feature interaction over heterogeneous user, item, context, and cross features, and…
arXiv:2609.39828v1 Announce Type: new Abstract: Generative recommendation, has been attracted a surge of attentions in industrial and academic research community, towards to build more smart system to build…
arXiv:2609.27297v2 Announce Type: replace-cross Abstract: Agentic science envisions many autonomous agents investigating concurrently while building on a shared, evolving body of scientific knowledge. This requires a…
arXiv:2609.40069v1 Announce Type: cross Abstract: Generative Engine Optimization (GEO) shapes content to increase its likelihood of being cited by answer engines built on retrieval-augmented large language models. GEO…
arXiv:2609.39312v1 Announce Type: new Abstract: Generative retrieval with semantic identifiers (SIDs) makes successive decisions over a document hierarchy. Relevant documents for the same query may share coarse prefixes…
arXiv:2609.38949v1 Announce Type: new Abstract: Text-video retrieval, which aims to bridge visual and textual modalities by learning a joint embedding space, has become a crucial task in multimodal intelligence. Despite…
arXiv:2609.19942v2 Announce Type: replace-cross Abstract: In extractive document question answering whose questions were generated from the passages that contain their answers -- so that retrieval recovers 92-99.8% of…
45 items available
