Related papers: Self-seeding and Multi-intent Self-instructing LLM…

Large language models (LLMs) have emerged as powerful and general solutions to many natural language tasks. However, many of the most important applications of language generation are interactive, where an agent has to talk to a person to…

Intent-aware session recommendation (ISR) is pivotal in discerning user intents within sessions for precise predictions. Traditional approaches, however, face limitations due to their presumption of a uniform number of intents across all…

Deep Research (DR) agents extend Large Language Models (LLMs) beyond parametric knowledge by autonomously retrieving and synthesizing evidence from large web corpora into long-form reports, enabling a long-horizon agentic paradigm. However,…

Automating data generation with Large Language Models (LLMs) has become increasingly popular. In this work, we investigate the feasibility and effectiveness of LLM-based data generation in the challenging setting of source-grounded…

Conversational news recommendation requires grounding each suggestion in a rapidly evolving article corpus while addressing implicit user intents that lack explicit retrievable keywords. To characterize this scenario, we identify 6 intent…

Log data can reveal valuable information about how users interact with Web search services, what they want, and how satisfied they are. However, analyzing user intents in log data is not easy, especially for emerging forms of Web search…

Large Language Models (LLMs) have exhibited impressive capabilities across diverse application domains. Recent work has explored Multi-LLM Agent Debate (MAD) as a way to enhance performance by enabling multiple LLMs to discuss and refine…

The utility of synthetic data to enhance pretraining data quality and hence to improve downstream task accuracy has been widely explored in recent large language models (LLMs). Yet, these approaches fall inadequate in complex, multi-hop and…

Discovering customer intentions is crucial for automated service agents, yet existing intent clustering methods often fall short due to their reliance on embedding distance metrics and neglect of underlying semantic structures. To address…

The rise of Large Language Models (LLMs) and generative visual analytics systems has transformed data-driven insights, yet significant challenges persist in accurately interpreting users' analytical and interaction intents. While language…

Task-oriented Dialogue Systems (TODS) often face the challenge of encountering new intents. New Intent Discovery (NID) is a crucial task that aims to identify these novel intents while maintaining the capability to recognize existing ones.…

Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models are trained on diverse academic papers and reports, they are not exposed to the reasoning processes…

Understanding human intents from multimodal signals is critical for analyzing human behaviors and enhancing human-machine interactions in real-world scenarios. However, existing methods exhibit limitations in their modality-level reliance,…

This paper introduces SOLID (Synergizing Optimization and Large Language Models for Intelligent Decision-Making), a novel framework that integrates mathematical optimization with the contextual capabilities of large language models (LLMs).…

Recently, ``textless" speech language models (SLMs) based on speech units have made huge progress in generating naturalistic speech, including non-verbal vocalizations. However, the generated speech samples often lack semantic coherence. In…

Speech Language Models (SLMs) exhibit strong semantic understanding, yet their generated speech often sounds flat and fails to convey expressive intent, undermining user engagement. We term this mismatch the semantic understanding-acoustic…

Previous in-context learning (ICL) research has focused on tasks such as classification, machine translation, text2table, etc., while studies on whether ICL can improve human-like dialogue generation are scarce. Our work fills this gap by…

Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging. Instructing tuning, i.e. tuning models on instruction and sample responses generated by humans…

Intent, typically clearly formulated and planned, functions as a cognitive framework for communication and problem-solving. This paper introduces the concept of Speaking with Intent (SWI) in large language models (LLMs), where the…

Personalized dialogue systems have gained significant attention in recent years for their ability to generate responses in alignment with different personas. However, most existing approaches rely on pre-defined personal profiles, which are…