Related papers: Data-Aware Socratic Query Refinement in Database S…

For decades, SQL has been the default language for composing queries, but it is increasingly used as an artifact to be read and verified rather than authored. With Large Language Models (LLMs), queries are increasingly machine-generated,…

End-to-end speech-in speech-out dialogue systems are emerging as a powerful alternative to traditional ASR-LLM-TTS pipelines, generating more natural, expressive responses with significantly lower latency. However, these systems remain…

Conversational agents often encounter ambiguous user requests, requiring an effective clarification to successfully complete tasks. While recent advancements in real-world applications favor multi-agent architectures to manage complex…

We propose a new approach for modeling and reconciling conflicting data cleaning actions. Such conflicts arise naturally in collaborative data curation settings where multiple experts work independently and then aim to put their efforts…

A multi-disciplinary understanding of the concepts of identity, agency, relationships, interactions, and information could help us develop mitigation strategies for responsible human-algorithmic systems in the field of AI. It is imperative…

The conventional use of the Retrieval-Augmented Generation (RAG) architecture has proven effective for retrieving information from diverse documents. However, challenges arise in handling complex table queries, especially within PDF…

Rationalization empowers deep learning models with self-explaining capabilities through a cooperative game, where a generator selects a semantically consistent subset of the input as a rationale, and a subsequent predictor makes predictions…

NL2SQL systems deployed in industry settings often encounter ambiguous or unanswerable queries, particularly in interactive scenarios with incomplete user clarification. Existing benchmarks typically assume a single source of ambiguity and…

Retrieval-Augmented Generation (RAG) enhances the factual grounding of Large Language Models by conditioning their outputs on external documents. However, standard embedding-based retrievers treat naturally structured corpora, such as…

Cascaded Automatic Speech Recognition -- Large Language Model (ASR-LLM) pipelines remain popular for industrial Spoken Dialogue Systems (SDS), primarily because their decoupled design ensures perceptual verifiability. However, cascaded…

The schema-guided paradigm overcomes scalability issues inherent in building task-oriented dialogue (TOD) agents with static ontologies. Instead of operating on dialogue context alone, agents have access to hierarchical schemas containing…

Retrieval-augmented generation (RAG) often falls short when retrieved context includes confusing semi-relevant passages, or when answering questions require deep contextual understanding and reasoning. We propose an efficient fine-tuning…

Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful…

Active learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost. This is now an essential tool for building low-resource syntactic analyzers such as part-of-speech (POS) taggers. Existing…

In spoken Task-Oriented Dialogue (TOD) systems, the choice of the semantic representation describing the users' requests is key to a smooth interaction. Indeed, the system uses this representation to reason over a database and its domain…

Access to humanities research databases is often hindered by the limitations of traditional interaction formats, particularly in the methods of searching and response generation. This study introduces an LLM-based smart assistant designed…

Agentic Retrieval-Augmented Generation (RAG) empowers large language models to autonomously plan and retrieve information for complex problem-solving. However, the development of robust agents is hindered by the scarcity of high-quality…

We present Deep Search DocQA. This application enables information extraction from documents via a question-answering conversational assistant. The system integrates several technologies from different AI disciplines consisting of document…

Dialogue data in real scenarios tend to be sparsely available, rendering data-starved end-to-end dialogue systems trained inadequately. We discover that data utilization efficiency in low-resource scenarios can be enhanced by mining…

Data users need relevant context and research expertise to effectively search for and identify relevant datasets. Leading data providers, such as the Inter-university Consortium for Political and Social Research (ICPSR), offer standardized…