arXiv:2602.08826v2 Announce Type: replace
Abstract: Large language models (LLMs) have been widely applied to emotional support conversation (ESC). However, complex multi-turn support remains challenging.This is because existing alignment schemes rely …
arXiv:2603.08182v2 Announce Type: replace
Abstract: Large language models often underperform in many European languages due to the dominance of English and a few high-resource languages in training data. This paper presents TildeOpen LLM, a 30-billion…
arXiv:2604.26312v1 Announce Type: new
Abstract: Public opinion towards the Free Nutritious Meal Program (MBG) on YouTube social media reflects diverse community responses. This study applies the Long Short-Term Memory (LSTM) method to classify sentime…
arXiv:2604.00706v2 Announce Type: replace
Abstract: Assessing the veracity of a claim made online is a complex and important task with real-world implications. When these claims are directed at communities with limited access to information and the co…
arXiv:2412.13682v5 Announce Type: replace-cross
Abstract: Travel planning stands out among real-world applications of \emph{Language Agents} because it couples significant practical demand with a rigorous constraint-satisfaction challenge. However, ex…
arXiv:2602.23163v3 Announce Type: replace-cross
Abstract: Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to detect and quan…
arXiv:2604.26412v1 Announce Type: new
Abstract: Speculative decoding accelerates LLM inference, but SOTA hidden-state-based drafters suffer from long-range decay: draft accuracy degrades as the speculative step increases. Existing work attributes this…
arXiv:2409.00557v4 Announce Type: replace
Abstract: Equipped with the capability to call functions, modern large language models (LLMs) can leverage external tools for addressing a range of tasks unattainable through language skills alone. However, th…
arXiv:2604.26500v1 Announce Type: new
Abstract: LLMs and speech assistants are increasingly used for task-oriented interactions, yet their evaluation often relies on controlled scenarios that fail to capture the variability and complexity of real user…
arXiv:2502.11614v3 Announce Type: replace
Abstract: Prior studies have shown that distinguishing text generated by Large Language Models (LLMs) from human-written one is highly challenging for humans, and often no better than random guessing. To verif…