Related papers: CORE-T: COherent REtrieval of Tables for Text-to-S…

Retrieval-Augmented Generation (RAG) has demonstrated considerable effectiveness in open-domain question answering. However, when applied to heterogeneous documents, comprising both textual and tabular components, existing RAG approaches…

Tabular data synthesis involves not only multi-table synthesis but also generating multi-modal data (e.g., strings and categories), which enables diverse knowledge synthesis. However, separating numerical and categorical data has limited…

Standard decoding in Masked Diffusion Models (MDMs) is hindered by context rigidity: tokens are retained based on transient high confidence, often ignoring that early predictions lack full context. This creates cascade effects where initial…

Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result,…

Dense retrieval (DR) has the potential to resolve the query understanding challenge in conversational search by matching in the learned embedding space. However, this adaptation is challenging due to DR models' extra needs for supervision…

Table-text retrieval aims to retrieve relevant tables and text to support open-domain question answering. Existing studies use either early or late fusion, but face limitations. Early fusion pre-aligns a table row with its associated…

Advancements in Large Language Models (LLMs) have extended their input context length, yet they still struggle with retrieval and reasoning in long-context inputs. Existing methods propose to utilize the prompt strategy and retrieval head…

Translating natural language utterances to executable queries is a helpful technique in making the vast amount of data stored in relational databases accessible to a wider range of non-tech-savvy end users. Prior work in this area has…

We present Cross-lingual Open-Retrieval Answer Generation (CORA), the first unified many-to-many question answering (QA) model that can answer questions across many languages, even for ones without language-specific annotated data or…

With the rapid advancement of large language models (LLMs), growing efforts have been made on LLM-based table retrieval. However, existing studies typically focus on single-table query, and implement it by similarity matching after encoding…

Despite advances in large language model (LLM)-based natural language interfaces for databases, scaling to enterprise-level data catalogs remains an under-explored challenge. Prior works addressing this challenge rely on domain-specific…

Search systems are increasingly used for reasoning-intensive queries, where what makes a document relevant requires understanding or reasoning over the query-document relation rather than relying on surface vocabulary or topical similarity.…

Dense retrieval has been shown to be effective for retrieving relevant documents for Open Domain QA, surpassing popular sparse retrieval methods like BM25. REALM (Guu et al., 2020) is an end-to-end dense retrieval system that relies on MLM…

While recent advancements in inference-time learning have improved LLM reasoning on Text-to-SQL tasks, current solutions still struggle to perform well on the most challenging tasks in the Bird-Bench (BIRD) benchmark. This is due to…

Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g. prompt optimization) approaches to doing so typically require hundreds of training…

Serving large language models (LLMs) efficiently remains challenging due to the high memory and latency overhead of key-value (KV) cache access during autoregressive decoding. We present \textbf{TinyServe}, a lightweight and extensible…

The advancements of Large language models (LLMs) have provided great opportunities to text-to-SQL tasks to overcome the main challenges to understand complex domain information and complex database structures in business applications. In…

Recently, DeepSeek-R1 (671B) (DeepSeek-AIet al., 2025) has demonstrated its excellent reasoning ability in complex tasks and has publiclyshared its methodology. This provides potentially high-quality chain-of-thought (CoT) data for…

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. However, incorporating a large volume of retrieved documents…

Tensor algebra is widely used in many applications, such as scientific computing, machine learning, and data analytics. The tensors represented real-world data are usually large and sparse. There are tens of storage formats designed for…