arXiv:2604.19071v1 Announce Type: new
Abstract: Evaluating the writing capabilities of large language models (LLMs) remains a significant challenge due to the multidimensional nature of writing skills and the limitations of existing metrics. LLM’s per…
arXiv:2411.18275v2 Announce Type: replace
Abstract: Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities. However, these models remain highly vulnerable to adversarial attacks. While exi…
arXiv:2604.19151v1 Announce Type: new
Abstract: Existing Indic ASR benchmarks often use scripted, clean speech and leaderboard driven evaluation that encourages dataset specific overfitting. In addition, strict single reference WER penalizes natural s…
arXiv:2604.16654v2 Announce Type: replace
Abstract: Reclaimed slur usage is a common and meaningful practice online for many marginalized communities. It serves as a source of solidarity, identity, and shared experience. However, contemporary automate…
arXiv:2604.19189v1 Announce Type: new
Abstract: For news headlines to influence beliefs and drive action, relevant information needs to be retained and retrievable from memory. In this probing study we draw on experiment designs from cognitive psychol…
arXiv:2512.16059v2 Announce Type: replace-cross
Abstract: In-Context Learning (ICL) has become a standard technique for adapting Large Language Models (LLMs) to specialized tasks by supplying task-specific exemplars within the prompt. However, when th…
arXiv:2602.12735v2 Announce Type: replace-cross
Abstract: Effectively retrieving, reasoning, and understanding multimodal information remains a critical challenge for agentic systems. Traditional Retrieval-augmented Generation (RAG) methods rely on li…
arXiv:2604.18712v1 Announce Type: new
Abstract: Probing has shown that language model representations encode rich linguistic information, but it remains unclear whether they also capture cognitive signals about human processing. In this work, we probe…
arXiv:2604.19351v1 Announce Type: new
Abstract: The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compression me…
arXiv:2604.19394v1 Announce Type: new
Abstract: This paper narrows the performance gap between small, specialized models and significantly larger general-purpose models through domain adaptation via continual pre-training and merging. We address the s…