相关论文: LingVarBench: Benchmarking LLMs on Entity Recognit…

Segmenting speech transcripts into thematic sections benefits both downstream processing and users who depend on written text for accessibility. We introduce a novel approach to hierarchical topic segmentation in transcripts, generating…

Audio generation has made significant progress, yet synthesizing unified audio where speech and sounds are naturally composited remains a challenge. Current methods either rely on disjoint pipelines, which fail to capture fine-grained…

Large language models (LLMs) have shown superb capability of modeling multimodal signals including audio and text, allowing the model to generate spoken or textual response given a speech input. However, it remains a challenge for the model…

Large language models (LLMs) have been proven capable of memorizing their training data, which can be extracted through specifically designed prompts. As the scale of datasets continues to grow, privacy risks arising from memorization have…

As Large Language Models (LLMs) are increasingly deployed as task-oriented agents in enterprise environments, ensuring their strict adherence to complex, domain-specific operational guidelines is critical. While utilizing an LLM-as-a-Judge…

Large Language Models (LLMs) are machine learning models that have seen widespread adoption due to their capability of handling previously difficult tasks. LLMs, due to their training, are sensitive to how exactly a question is presented,…

Current benchmarks for evaluating Large Language Models (LLMs) often do not exhibit enough writing style diversity, with many adhering primarily to standardized conventions. Such benchmarks do not fully capture the rich variety of…

Entity Linking (EL), the task of mapping textual entity mentions to their corresponding entries in knowledge bases, constitutes a fundamental component of natural language understanding. Recent advancements in Large Language Models (LLMs)…

Large language models (LLMs) deployed in user-facing applications require long-horizon consistency: the ability to remember prior interactions, respect user preferences, and ground reasoning in past events. However, contemporary memory…

Although pretrained language models (PLMs) can be prompted to perform a wide range of language tasks, it remains an open question how much this ability comes from generalizable linguistic understanding versus surface-level lexical patterns.…

Extracting clinically relevant information from unstructured medical narratives such as admission notes, discharge summaries, and emergency case histories remains a challenge in clinical natural language processing (NLP). Medical Entity…

Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars. However, in low-resource languages, obtaining such hand-picked exemplars can still be challenging, where unsupervised techniques may be…

Building on the success of large language models (LLMs), recent advancements such as GPT-4o have enabled real-time speech interactions through LLM-based voice assistants, offering a significantly improved user experience compared to…

Virtual Assistants (VAs) are important Information Retrieval platforms that help users accomplish various tasks through spoken commands. The speech recognition system (speech-to-text) uses query priors, trained solely on text, to…

Financial documents like earning reports or balance sheets often involve long tables and multi-page reports. Large language models have become a new tool to help numerical reasoning and understanding these documents. However, prompt quality…

Large language models (LLMs) are increasingly used as human simulators, both for evaluating conversational systems and for generating fine-tuning data. However, naive "act-as-a-user" prompting often yields verbose, unrealistic utterances,…

Static benchmarks for harmful content detection face limitations in scalability and diversity, and may also be affected by contamination from web-scale pre-training corpora. To address these issues, we propose a framework for synthesizing…

This paper studies contextual biasing with Large Language Models (LLMs), where during second-pass rescoring additional contextual information is provided to a LLM to boost Automatic Speech Recognition (ASR) performance. We propose to…

This paper explores the development and application of an automated system designed to extract information from semi-structured interview transcripts. Given the labor-intensive nature of traditional qualitative analysis methods, such as…

The widespread adoption of large language models (LLMs) in healthcare raises critical questions about their ability to interpret patient-generated narratives, which are often informal, ambiguous, and noisy. Existing benchmarks typically…