Latest AI/ML News
2784 articles · arXiv cs.CL
arXiv:2609.20827v1 Announce Type: new Abstract: Hospital discharge education is an interactive teaching task: a clinician adapts a discharge plan to a…
arXiv:2609.20824v1 Announce Type: new Abstract: We explore whether entropy-based confidence signals can be leveraged to improve the accuracy of Small…
arXiv:2609.18766v2 Announce Type: replace-cross Abstract: Large audio-language models have shown promise for anti-fraud detection by directly processi…
arXiv:2609.18748v2 Announce Type: replace-cross Abstract: Telecom fraud scripts evolve rapidly and are often designed to resemble routine service conv…
arXiv:2608.26171v2 Announce Type: replace-cross Abstract: Multi-stage LLM hiring pipelines (resume improvement, interview question generation, answer…
arXiv:2606.11176v2 Announce Type: replace-cross Abstract: Data tells stories that shape society; the data journalist's job is to turn raw information…
arXiv:2604.15097v4 Announce Type: replace-cross Abstract: This beta technical report asks how reusable experience should be represented so that it can…
arXiv:2505.16180v3 Announce Type: replace-cross Abstract: Evaluating image captions requires cohesive assessment of both visual semantics and language…
arXiv:2609.18310v2 Announce Type: replace Abstract: We introduce Nemotron-SEA-LION-v4.8, a family of Southeast Asian Languages In One Network (SEA-LIO…
arXiv:2609.18304v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly tackle long-horizon tasks through multi-step enviro…
arXiv:2609.16900v2 Announce Type: replace Abstract: Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decom…
arXiv:2609.15964v2 Announce Type: replace Abstract: Large language models (LLMs) have been widely adopted for clinical question answering (QA). Curren…
arXiv:2609.15369v2 Announce Type: replace Abstract: Word-level detectors identify unedited AI-generated text almost perfectly, but the literature docu…
arXiv:2609.15188v3 Announce Type: replace Abstract: LLMs have been able to generate fluent prose, but high-quality stories also require coordinated de…
arXiv:2609.13445v2 Announce Type: replace Abstract: Speech-to-speech LLMs like Moshi, and its derivative PersonaPlex, can listen and speak concurrentl…
arXiv:2608.12913v2 Announce Type: replace Abstract: Contrastive Decoding (CD) improves generation quality, but its amateur-model pass makes decoding e…
arXiv:2608.12776v2 Announce Type: replace Abstract: This paper introduces ViTOED, a novel dataset for target-oriented emotion detection in Vietnamese…
arXiv:2606.30175v2 Announce Type: replace Abstract: The continuous evolution of large language models drives escalating demands on data scale and qual…
arXiv:2606.29960v2 Announce Type: replace Abstract: Large Language Models (LLMs) often fail to maintain instruction hierarchies (IH) when processing m…
arXiv:2606.11639v2 Announce Type: replace Abstract: As automatic speech recognition (ASR) systems shift toward multilingual support and low-resource l…