Related papers: CLIPPER: Compression enables long-context syntheti…

Large Language Models (LLMs) have democratized synthetic data generation, which in turn has the potential to simplify and broaden a wide gamut of NLP tasks. Here, we tackle a pervasive problem in synthetic data generation: its generative…

Encoder-decoder Large Language Models (LLMs), such as BERT and RoBERTa, require that all categories in an annotation task be sufficiently represented in the training data for optimal performance. However, it is often difficult to find…

Fighting misinformation is a challenging, yet crucial, task. Despite the growing number of experts being involved in manual fact-checking, this activity is time-consuming and cannot keep up with the ever-increasing amount of Fake News…

Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and inefficient. In this paper, we introduce Compressed Latent…

In the midst of widespread misinformation and disinformation through social media and the proliferation of AI-generated texts, it has become increasingly difficult for people to validate and trust information they encounter. Many…

Reliable evaluation protocols are of utmost importance for reproducible NLP research. In this work, we show that sometimes neither metric nor conventional human evaluation is sufficient to draw conclusions about system performance. Using…

Prior research on training grounded factuality classification models to detect hallucinations in large language models (LLMs) has relied on public natural language inference (NLI) data and synthetic data. However, conventional NLI datasets…

Injecting world knowledge into pretrained multimodal large language models (MLLMs) is essential for domain-specific applications. Task-specific fine-tuning achieves this by tailoring MLLMs to high-quality in-domain data but encounters…

Large Reasoning Models (LRMs) have demonstrated impressive capabilities but suffer from cognitive inefficiencies like "overthinking" simple problems and "underthinking" complex ones. While existing methods that use supervised fine-tuning…

In fact-checking, structure and phrasing of claims critically influence a model's ability to predict verdicts accurately. Social media content in particular rarely serves as optimal input for verification systems, which necessitates…

Retrieval-augmented generation (RAG) can supplement large language models (LLMs) by integrating external knowledge. However, as the number of retrieved documents increases, the input length to LLMs grows linearly, causing a dramatic…

Complex claim verification requires decomposing sentences into verifiable subclaims, yet existing methods struggle to align decomposition quality with verification performance. We propose a reinforcement learning (RL) approach that jointly…

Large Language Models (LLMs) have recently exhibited remarkable reasoning capabilities, largely enabled by supervised fine-tuning (SFT)- and reinforcement learning (RL)-based post-training on high-quality reasoning data. However,…

Search applications often display shortened sentences which must contain certain query terms and must fit within the space constraints of a user interface. This work introduces a new transition-based sentence compression technique developed…

Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…

Large language models (LLMs) offer significant potential to accelerate systematic literature reviews (SLRs), yet current approaches often rely on brittle, manually crafted prompts that compromise reliability and reproducibility. This…

Large language models have achieved substantial progress in mathematical reasoning, yet their advancement is limited by the scarcity of high-quality, high-difficulty training data. Existing synthesis methods largely rely on transforming…

A popular approach to sentence compression is to formulate the task as a constrained optimization problem and solve it with integer linear programming (ILP) tools. Unfortunately, dependence on ILP may make the compressor prohibitively slow,…

Large Language Models (LLMs) have been increasingly employed for query expansion. However, their generative nature often undermines performance on complex multi-hop retrieval tasks by introducing irrelevant or noisy information. To address…

While LLMs demonstrate remarkable fluency in narrative generation, existing methods struggle to maintain global narrative coherence, contextual logical consistency, and smooth character development, often producing monotonous scripts with…