Latest AI/ML News
2637 articles · 🧠 Research
arXiv:2608.18011v1 Announce Type: new Abstract: Reasoning in LLMs is overwhelmingly studied in domains that provide a model with rules: mathematics an…
arXiv:2608.17994v1 Announce Type: new Abstract: Using LLMs as judges has become standard practice for evaluating model outputs at scale. This is parti…
arXiv:2608.17979v1 Announce Type: new Abstract: Authorship verification (AV) assumes that an author's writing style remains sufficiently stable to dis…
arXiv:2608.17950v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate remarkable multi-hop reasoning capabilities over long context…
arXiv:2608.17938v1 Announce Type: new Abstract: Small language models can grade open-ended examination answers as reliably as substantially more expen…
arXiv:2608.17931v1 Announce Type: new Abstract: Recent advances in AI have revolutionized speech processing, yet effective speech understanding requir…
arXiv:2608.17911v1 Announce Type: new Abstract: As LLM agents operate across structured workflows and sessions, preserving long-term history does not…
arXiv:2608.17895v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have made significant strides in visual comprehension,…
arXiv:2608.17866v1 Announce Type: new Abstract: Reconstructing prompts that can elicit a desired answer or behaviour in an LLM is an open and importan…
arXiv:2608.17843v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong performance on structured reasoning tasks, but w…
arXiv:2608.17827v1 Announce Type: new Abstract: Public institutions face a persistent challenge in selecting LLMs suited to their specific context. Ex…
arXiv:2608.17810v1 Announce Type: new Abstract: The evaluation of large language models (LLMs) relies heavily on human-designed assessments, implicitl…
arXiv:2608.17809v1 Announce Type: new Abstract: Humans naturally form and express beliefs in daily communication, e.g., "I think the answer is 3" or "…
arXiv:2608.17795v1 Announce Type: new Abstract: Text-to-SQL systems are commonly evaluated using ground-truth SQL queries or reference execution resul…
arXiv:2608.17781v1 Announce Type: new Abstract: ML systems increasingly condition decisions on downstream model identity, but this is useful only if m…
arXiv:2608.17744v1 Announce Type: new Abstract: Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters eac…
arXiv:2608.17605v1 Announce Type: new Abstract: Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In…
arXiv:2608.17587v1 Announce Type: new Abstract: Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perfor…
arXiv:2608.17583v1 Announce Type: new Abstract: Online video platforms can expose young users to harmful content, but independent audits remain diffic…
arXiv:2608.17536v1 Announce Type: new Abstract: Legal consultation questions exhibit multi-level complexity. A single retrieval strategy often leads t…