Latest AI/ML News
2784 articles · arXiv cs.CL
arXiv:2609.11131v1 Announce Type: new Abstract: Human simultaneous interpreting (SI) is commonly assessed with analytic rubrics separating meaning tra…
arXiv:2609.11128v1 Announce Type: new Abstract: In disinformation datasets, narratives are often understood as recurring interpretive patterns that gr…
arXiv:2609.11117v1 Announce Type: new Abstract: Reproducibility is essential to scientific progress, yet the growing volume and complexity of scientif…
arXiv:2609.11101v1 Announce Type: new Abstract: Dispute mediation is essential for maintaining social harmony and resilience, yet developing skilled m…
arXiv:2609.11067v1 Announce Type: new Abstract: Large language models are increasingly used as judges to measure social bias in text, yet the passages…
arXiv:2609.11029v1 Announce Type: new Abstract: Large language models are typically trained under uniform token weighting, which allows frequent and l…
arXiv:2609.11020v1 Announce Type: new Abstract: We study K/V-cache interventions -- transplanting a target-conditioned K/V trajectory into a source-pe…
arXiv:2609.10996v1 Announce Type: new Abstract: Verbalized confidence, long dismissed as overconfident, coarse, and prone to round-number clustering,…
arXiv:2609.10993v1 Announce Type: new Abstract: Multilingual large language models (mLLMs) contain a small fraction of feed-forward neurons that are s…
arXiv:2609.10950v1 Announce Type: new Abstract: Recent multimodal sentiment analysis studies increasingly adopt text-centric fusion approaches to expl…
arXiv:2609.10934v1 Announce Type: new Abstract: Turn-taking is a fundamental mechanism that governs when interlocutors speak and listen. Although Spok…
arXiv:2609.10923v1 Announce Type: new Abstract: Graph captions should help readers understand graph structure, rather than simply translate adjacency…
arXiv:2609.10922v1 Announce Type: new Abstract: Auto-research agents have shown the potential to automate hypothesis generation, experiment execution,…
arXiv:2609.10901v1 Announce Type: new Abstract: LLM search agents are often evaluated on final-answer accuracy, overlooking the process. Analyzing a s…
arXiv:2609.10896v1 Announce Type: new Abstract: Speech-based automatic detection of Alzheimer's disease (AD) provides a non-invasive and scalable appr…
arXiv:2609.10893v1 Announce Type: new Abstract: Recent advances in large language models have transformed human-computer interaction. Despite their fl…
arXiv:2609.10830v1 Announce Type: new Abstract: When a language model finds a sentence unusually cheap to predict, it is tempting to conclude that the…
arXiv:2609.10810v1 Announce Type: new Abstract: Minimal-edit Grammatical Error Correction (GEC) is a challenging task for zero- and few-shot prompted…
arXiv:2609.10792v1 Announce Type: new Abstract: Transformer-based models excel at Automatic Readability Assessment (ARA), yet feature-based models rem…
arXiv:2609.10758v1 Announce Type: new Abstract: Multilingual large language models (LLMs) are increasingly used for open-ended text generation, yet th…