相关论文: OntoGUM: Evaluating Contextualized SOTA Coreferenc…

Vision-Language Models (VLMs) are expensive because the LLM processes hundreds of largely redundant visual tokens. Existing token reduction methods typically exploit \textit{either} vision-encoder saliency (broad but query-agnostic)…

Determining and ranking the most salient entities in a text is critical for user-facing systems, especially as users increasingly rely on models to interpret long documents they only partially read. Graded entity salience addresses this…

Robust unlearning is crucial for safely deploying large language models (LLMs) in environments where data privacy, model safety, and regulatory compliance must be ensured. Yet the task is inherently challenging, partly due to difficulties…

The screen content images (SCIs) usually comprise various content types with sharp edges, in which the artifacts or distortions can be well sensed by the vanilla structure similarity measurement in a full reference manner. Nonetheless,…

With their vast open-world knowledge and reasoning abilities, large language models (LLMs) have become a promising tool for sequential recommendation. Researchers have explored various methods to harness these capabilities, but most…

Text-to-image customization, which aims to synthesize text-driven images for the given subjects, has recently revolutionized content creation. Existing works follow the pseudo-word paradigm, i.e., represent the given subjects as…

Comparing bridging annotations across coreference resources is difficult, largely due to a lack of standardization across definitions and annotation schemas and narrow coverage of disparate text domains across resources. To alleviate domain…

Textual domain is a crucial property within the Natural Language Processing (NLP) community due to its effects on downstream model performance. The concept itself is, however, loosely defined and, in practice, refers to any non-typological…

Generative recommendation has emerged as a scalable alternative to traditional retrieve-and-rank pipelines by operating in a compact token space. However, existing methods mainly rely on discrete code-level supervision, which leads to…

Retrieval-augmented generation (RAG) enhances the question-answering (QA) abilities of large language models (LLMs) by integrating external knowledge. However, adapting general-purpose RAG systems to specialized fields such as science and…

The quality of meeting summaries generated by natural language generation (NLG) systems is hard to measure automatically. Established metrics such as ROUGE and BERTScore have a relatively low correlation with human judgments and fail to…

Ensuring that Large Language Models (LLMs) generate summaries faithful to a given source document is essential for real-world applications. While prior research has explored LLM faithfulness, existing benchmarks suffer from annotation…

We study the limitations of Large Language Models (LLMs) for the task of response generation in human-machine dialogue. Several techniques have been proposed in the literature for different dialogue types (e.g., Open-Domain). However, the…

Large-scale coreference resolution presents a significant challenge in natural language processing, necessitating a balance between efficiency and accuracy. In response to this challenge, we introduce an End-to-End Neural Coreference…

Retrieval-Augmented Generation (RAG) has emerged as a crucial framework in natural language processing (NLP), improving factual consistency and reducing hallucinations by integrating external document retrieval with large language models…

Ambiguous words or underspecified references require interlocutors to resolve them, often by relying on shared context and commonsense knowledge. Therefore, we systematically investigate whether Large Language Models (LLMs) can leverage…

Ensuring native-like quality of large language model (LLM) responses across many languages is challenging. To address this, we introduce MENLO, a framework that operationalizes the evaluation of native-like response quality based on…

Large language models (LLMs) typically utilize the top-k contexts from a retriever in retrieval-augmented generation (RAG). In this work, we propose a novel instruction fine-tuning framework RankRAG, which instruction-tunes a single LLM for…

Non-Orthogonal Multiple Access (NOMA) technology has emerged as a promising technology to enable massive connectivity and enhanced spectral efficiency in next-generation wireless networks. In this study, we propose a novel two-user downlink…

Large language models (LLMs) are being increasingly adopted in the software engineering domain, yet the robustness of their grasp on core software design concepts remains unclear. We conduct an empirical study to systematically evaluate…