Related papers: Purely Semantic Indexing for LLM-based Generative …

Large Language Models (LLMs) have demonstrated impressive quality when applied to predictive tasks such as relevance ranking and semantic search. However, deployment of such LLMs remains prohibitively expensive for industry applications…

Generative recommendation treats next-item prediction as autoregressive item-identifier generation. Specifically, items are encoded as semantic identifiers (SIDs), which are short coarse-to-fine token sequences whose early tokens capture…

Recommender systems are essential for guiding users through the vast and diverse landscape of digital content by delivering personalized and relevant suggestions. However, improving both personalization and interpretability remains a…

Recent advances have explored visual token pruning to accelerate the inference of large vision-language models (LVLMs). However, existing methods often struggle to balance token importance and diversity: importance-based methods tend to…

We introduce and address the problem of ad hoc table retrieval: answering a keyword query with a ranked list of tables. This task is not only interesting on its own account, but is also being used as a core component in many other…

Generative retrieval, which is a new advanced paradigm for document retrieval, has recently attracted research interests, since it encodes all documents into the model and directly generates the retrieved documents. However, its power is…

Scientific retrieval is essential for advancing scientific knowledge discovery. Within this process, document reranking plays a critical role in refining first-stage retrieval results. However, standard LLM listwise reranking faces…

Automated assessment of open-ended student responses is a critical capability for scaling personalized feedback in education. While large language models (LLMs) have shown promise in grading tasks via in-context learning (ICL), their…

Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches…

Recent advances in Large Language Models (LLMs) have enhanced text-based recommendation by enriching traditional ID-based methods with semantic generalization capabilities. Text-based methods typically encode item textual information via…

Automatically highlighting words that cause semantic differences between two documents could be useful for a wide range of applications. We formulate recognizing semantic differences (RSD) as a token-level regression task and study three…

Retrieval-Augmented Generation (RAG) architectures have recently garnered significant attention for their ability to improve truth grounding and coherence in natural language processing tasks. However, the reliability of RAG systems in…

In this paper, we propose an intuitive, training-free and label-free method for intent clustering in conversational search. Current approaches to short text clustering use LLM-generated pseudo-labels to enrich text representations or to…

Considering query variance in information retrieval (IR) experiments is beneficial for retrieval effectiveness. Especially ranking ensembles based on different topically related queries retrieve better results than rankings based on a…

This paper addresses the limitations of traditional keyword-based search in understanding user intent and introduces a novel hybrid search approach that leverages the strengths of non-semantic search engines, Large Language Models (LLMs),…

We apply cross-lingual Latent Semantic Indexing to the Bilingual Document Alignment Task at WMT16. Reduced-rank singular value decomposition of a bilingual term-document matrix derived from known English/French page pairs in the training…

In retrieval-augmented generation (RAG) question answering systems, generating citations for large language model (LLM) outputs enhances verifiability and helps users identify potential hallucinations. However, we observe two problems in…

Incorporating collaborative information (CI) effectively is crucial for leveraging LLMs in recommendation tasks. Existing approaches often encode CI using soft tokens or abstract identifiers, which introduces a semantic misalignment with…

Recently, a novel generative retrieval (GR) paradigm has been proposed, where a single sequence-to-sequence model is learned to directly generate a list of relevant document identifiers (docids) given a query. Existing GR models commonly…

Large Language Models (LLMs) excel at capturing latent semantics and contextual relationships across diverse modalities. However, in modeling user behavior from sequential interaction data, performance often suffers when such semantic…