Topic - Edition
arXiv:2609.16912v1 Announce Type: new Abstract: We describe tus-nlp's Lit3R (Retrieve-Relate-Read) system for LitTraceQA, a shared task for literature-grounded question answering that requires systems to retrieve…
arXiv:2609.16814v1 Announce Type: cross Abstract: While Large Language Model (LLM)-based Natural Language Inference (NLI) systems achieve high accuracy, their decision-making processes lack auditable structures. This…
arXiv:2609.17366v1 Announce Type: cross Abstract: As technological and social innovations create novel regulatory challenges, legal systems grow in complexity - increasing the need for interfaces that enable effective…
arXiv:2609.16627v1 Announce Type: cross Abstract: Quantifying organizational environmental action from publicly available web content remains a challenging environmental data science problem because relevant information…
arXiv:2509.07801v5 Announce Type: replace-cross Abstract: Structured information extraction from scientific literature is crucial for capturing core concepts and emerging trends in specialized fields. While existing…
arXiv:2609.17043v1 Announce Type: cross Abstract: Multi-hop question answering requires combining information from multiple documents to answer complex questions. These systems have grown increasingly capable, yet when…
arXiv:2606.02737v3 Announce Type: replace Abstract: Dense retrieval compresses a passage into a single vector, but this compression is positionally skewed: early content dominates the embedding, and retrieval degrades…
arXiv:2609.13489v2 Announce Type: replace Abstract: RAG systems commonly retrieve a fixed number of documents (top-k) to ground generation, but this static approach is brittle: simple queries suffer over-retrieval…
arXiv:2609.16453v1 Announce Type: new Abstract: Agentic Retrieval-Augmented Generation (RAG) has become a promising paradigm for multi-hop question answering, where a reasoning model iteratively issues queries to a…
arXiv:2609.16730v1 Announce Type: cross Abstract: Conversational memory changes during use, so endpoint question answering alone cannot establish how a persistent state accumulates, ages, or incorporates revisions. We…
arXiv:2609.16847v1 Announce Type: cross Abstract: Region-level retrieval aims to align user-specified image regions with relevant regions or textual descriptions, playing a crucial role in realworld applications such as…
arXiv:2609.16304v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for product recommendation, but evaluating their recommendations presents challenges that differ from conventional…
arXiv:2609.16560v1 Announce Type: new Abstract: User behavior in real-world recommender systems is heterogeneous. While some users exhibit coherent preferences, others show abrupt interest shifts, bursty interactions,…
arXiv:2609.07595v2 Announce Type: replace-cross Abstract: The same underlying computational problem is solved across unrelated fields under different names: recursive Bayesian state estimation appears as a "Kalman…
arXiv:2609.13993v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong semantic understanding and preference reasoning capabilities, offering new opportunities for user modeling in recommender…
arXiv:2609.16391v1 Announce Type: new Abstract: Weight-only post-training quantization is the cheapest way to shrink a retrieval embedder, and the received advice for applying it -- protect the embedding table, allocate…
arXiv:2609.16407v1 Announce Type: new Abstract: On a delivery platform, personalized store ranking greatly influences what users find and order. Unlike digital-only domains, candidate stores are local and bound by…
arXiv:2609.16452v1 Announce Type: new Abstract: We propose a personalized capping framework (PCap) to improve the diversity in Facebook Marketplace by introducing user-level diversity constraints at the retrieval stage.…
arXiv:2609.16850v1 Announce Type: new Abstract: Given a user-item graph $G$, a query item $v_q$ and a target item $v_t$, the Swing score $sw(v_q, v_t)$ of the item pair $(v_q, v_t)$ leverages the user-item-user…
arXiv:2609.16607v1 Announce Type: new Abstract: Urban decision-support often asks whether activity is unusually high or low for a specific place, not which place has the larger raw count. Twenty pickups in a quiet…
24 items available
