Customer-obsessed science

Claim verification is a core component of automated fact-checking systems, aimed at determining the truthfulness of a statement by assessing it against reliable evidence sources such as documents or knowledge bases. This work presents KG-CRAFT, a method that improves automatic claim verification by leveraging large language models (LLMs) augmented with contrastive questions grounded in a knowledge graph

Composing messages in chatbot interactions is often time-consuming, making autocompletion an appealing way to reduce user effort. Different users have different preferences and therefore different expectations from autocompletion solutions. We study how personalization can improve the autocompletion process, evaluating four schemes defined along two axes: generation vs. ranking, and prior messages vs. external

Retrieval-Augmented Generation (RAG) systems degrade sharply under extreme noise, where irrelevant or redundant passages dominate. Current methods-fixed top-k retrieval, cross-encoder reranking, or policybased iteration-depend on static heuristics or costly reinforcement learning, failing to assess evidence sufficiency, detect subtle mismatches, or reduce redundancy, leading to hallucinations and poor grounding

High-quality search is essential for the success of online platforms, spanning e-commerce, social media, shopping-focused applications, and broader search systems such as content discovery and enterprise web search. To ensure optimal user experience and drive business growth, continuous evaluation and improvement of search systems is crucial. This paper introduces PROBES, a novel multi-task system powered

E-commerce search faces challenges such as sparse data and poor generalization from issues like multi-attribute resolution, multihop reasoning, and implicit intent. We propose iterative reranking as a compute-scaling strategy for LLM-based rankers, repeatedly applying listwise rankers to refine results by exploiting LLM non-determinism. Evaluated on three open datasets with three open-source LLMs, the method