Related papers: Incomplete Utterance Rewriting with Editing Operat…

Large Language Models (LLMs) struggle with long-context reasoning, not only due to the quadratic scaling of computational complexity with sequence length but also because of the scarcity and expense of annotating long-context data. There…

Reinforcement learning (RL) has driven recent breakthroughs in large language models (LLMs), especially for tasks where rewards can be computed automatically, such as code generation. However, it is less effective in open-ended medical…

Retrieval-Augmented Language Models (RALMs) have demonstrated significant potential in knowledge-intensive tasks; however, they remain vulnerable to performance degradation when presented with irrelevant or noisy retrieved contexts.…

We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the…

Transformative innovations in model architectures have introduced hierarchical embedding augmentation as a means to redefine the representation of tokens through multi-level semantic structures, offering enhanced adaptability to complex…

In neural text editing, prevalent sequence-to-sequence based approaches directly map the unedited text either to the edited text or the editing operations, in which the performance is degraded by the limited source text encoding and long,…

Long-form story generation task aims to produce coherent and sufficiently lengthy text, essential for applications such as novel writingand interactive storytelling. However, existing methods, including LLMs, rely on rigid outlines or lack…

We propose a design pattern for tackling text ranking problems, dubbed "Expando-Mono-Duo", that has been empirically validated for a number of ad hoc retrieval tasks in different domains. At the core, our design relies on pretrained…

Recent advances in large-scale text-to-image diffusion models (e.g., FLUX.1) have greatly improved visual fidelity in consistent character generation and editing. However, existing methods rarely unify these tasks within a single framework.…

Incremental learning is the ability of systems to acquire knowledge over time, enabling their adaptation and generalization to novel tasks. It is a critical ability for intelligent, real-world systems, especially when data changes…

Large Language Models (LLMs) are widely used for tasks such as natural language and code generation, but their outputs often suffer from issues like hallucination, toxicity, and incorrect results. Current libraries for structured LLM…

While guided decoding, especially value-guided methods, has emerged as a cost-effective alternative for controlling language model outputs without re-training models, its effectiveness is limited by the accuracy of the value function. We…

Text generation is the automated process of producing written or spoken language using computational methods. It involves generating coherent and contextually relevant text based on predefined rules or learned patterns. However, challenges…

The In-context generation paradigm recently has demonstrated strong power in instructional image editing with both data efficiency and synthesis quality. Nevertheless, shaping such in-context learning for instruction-based video editing is…

Structured data, rich in logical and relational information, has the potential to enhance the reasoning abilities of large language models (LLMs). Still, its integration poses a challenge due to the risk of overwhelming LLMs with excessive…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Instruction-tuning can be substantially optimized through enhanced diversity, resulting in models capable of handling a broader spectrum of tasks. However, existing data employed for such tuning often exhibit an inadequate coverage of…

Task-oriented dialogue (TOD) systems are commonly designed with the presumption that each utterance represents a single intent. However, this assumption may not accurately reflect real-world situations, where users frequently express…

Information Extraction (IE) from document images is challenging due to the high variability of layout formats. Deep models such as LayoutLM and BROS have been proposed to address this problem and have shown promising results. However, they…

We study multi-turn response generation for open-domain dialogues. The existing state-of-the-art addresses the problem with deep neural architectures. While these models improved response quality, their complexity also hinders the…