Related papers: BoundRL: Efficient Structured Text Segmentation th…

The growing complexity of legal cases has lead to an increasing interest in legal information retrieval systems that can effectively satisfy user-specific information needs. However, such downstream systems typically require documents to be…

Researchers have explored different ways to improve large language models (LLMs)' capabilities via dummy token insertion in contexts. However, existing works focus solely on the dummy tokens themselves, but fail to leverage the inherent…

Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary…

With the increasing prevalence of text generated by large language models (LLMs), there is a growing concern about distinguishing between LLM-generated and human-written texts in order to prevent the misuse of LLMs, such as the…

Large language models (LLMs) are being increasingly tuned to power complex generation tasks such as writing, fact-seeking, querying and reasoning. Traditionally, human or model feedback for evaluating and further tuning LLM performance has…

Automatic construction of relevant Knowledge Bases (KBs) from text, and generation of semantically meaningful text from KBs are both long-standing goals in Machine Learning. In this paper, we present ReGen, a bidirectional generation of…

To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most…

We propose a new framework, Translation between Augmented Natural Languages (TANL), to solve many structured prediction language tasks including joint entity and relation extraction, nested named entity recognition, relation classification,…

The rise of large language models (LLMs) has created an urgent need to distinguish between human-written and LLM-generated text to ensure authenticity and societal trust. Existing detectors typically provide a binary classification for an…

Recent advances in Large Language Models(LLMs) have enabled strong performance in long-form writing, but current training paradigms remain limited: Supervised Fine-Tuning (SFT) remains constrained by data saturation and performance…

Recent advancements in code generation have shown remarkable success across software domains, yet hardware description languages (HDLs) such as Verilog remain underexplored due to their concurrency semantics, syntactic rigidity, and…

Multimodal Large Language Models (MLLMs) have shown exceptional capabilities in vision-language tasks. However, effectively integrating image segmentation into these models remains a significant challenge. In this work, we propose a novel…

Long text classification is challenging for Large Language Models (LLMs) due to token limits and high computational costs. This study explores whether a Retrieval Augmented Generation (RAG) approach using only the most relevant text…

Understanding a Reinforcement Learning (RL) policy is crucial for ensuring that autonomous agents behave according to human expectations. This goal can be achieved using Explainable Reinforcement Learning (XRL) techniques. Although textual…

Multimodal Large Language Models (MLLMs) have shown exceptional capabilities in vision-language tasks; however, effectively integrating image segmentation into these models remains a significant challenge. In this paper, we introduce…

Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations. Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still…

Retrieval-Augmented Generation (RAG) systems commonly use chunking strategies for retrieval, which enhance large language models (LLMs) by enabling them to access external knowledge, ensuring that the retrieved information is up-to-date and…

Lexically constrained text generation is one of the constrained text generation tasks, which aims to generate text that covers all the given constraint lexicons. While the existing approaches tackle this problem using a lexically…

This paper presents a scene text detection technique that exploits bootstrapping and text border semantics for accurate localization of texts in scenes. A novel bootstrapping technique is designed which samples multiple 'subsections' of a…

Learning-based approaches for semantic segmentation have two inherent challenges. First, acquiring pixel-wise labels is expensive and time-consuming. Second, realistic segmentation datasets are highly unbalanced: some categories are much…