Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2607. 07003v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement even when incorrect.
arXiv:2607. 07469v1 Announce Type: cross Abstract: Fine-tuning large language models (LLMs) for e-commerce attribute extraction requires labeled data representative across thousands of product types, attributes, and multiple languages.
arXiv:2607. 07695v1 Announce Type: new Abstract: We introduce institutional red-teaming, an evaluation methodology for testing deployment rules in multi-agent AI: hold the agents, objectives, and task state fixed, vary only one rule, and attribute the resulting change in collective behavior to that rule.
arXiv:2607. 07184v1 Announce Type: cross Abstract: Pre-deployment safety evaluations aim to inform the downstream risks of releasing a new AI model.
arXiv:2510. 09595v3 Announce Type: replace Abstract: Competitive programming problems are increasingly used to evaluate the coding capabilities of large language models (LLMs) due to their complexity and ease of verification.
arXiv:2607. 06882v1 Announce Type: cross Abstract: Visual navigation policies built on large pretrained models have so far followed a common recipe: a dedicated visual encoder, a bespoke action head, and training on thousands of hours of cross-embodiment datasets.
arXiv:2607. 07026v1 Announce Type: new Abstract: Constrained decoding is essential for serving LLMs, ensuring that generated outputs follow specific structures such as JSON schema-formatted function calls.
arXiv:2607. 06713v1 Announce Type: cross Abstract: Large language models are rapidly moving towards closing the development cycle, transitioning from simple assistive companions to autonomous contributors deeply embedded into collaborative development environments.
arXiv:2602. 05088v4 Announce Type: replace Abstract: Millions of people now use generative AI chatbots for psychological support.
arXiv:2607. 07395v1 Announce Type: cross Abstract: Reliable confidence estimation remains a key limitation of test-time adaptation in vision-language models (VLMs), where prompt tuning improves zero-shot accuracy but often degrades calibration due to entropy-driven overconfidence.
arXiv:2607. 07521v1 Announce Type: cross Abstract: AI agents that generate final answers based on user input often do not meet the needs of creative fields.
arXiv:2607. 07027v1 Announce Type: cross Abstract: While generative models enable encoding of complex neuroimaging data for feature generation and reconstruction, developing optimal architectural frameworks with appropriate encoding and latent space processes is crucial for studying structural and functional properties of the brain.
arXiv:2607. 07405v1 Announce Type: new Abstract: Tool-using LLM agents can violate the very policies they are deployed to enforce while appearing to complete the task successfully.
arXiv:2607. 06605v1 Announce Type: new Abstract: Conformal prediction is being adopted in drug discovery to put an honest number on model reliability: pick an error rate alpha, and the method returns prediction sets containing the true label with probability at least 1 - alpha.
arXiv:2511. 23347v2 Announce Type: replace Abstract: An associative memory (AM) enables cue-response recall, and it has recently been recognized as a key mechanism underlying modern neural architectures such as Transformers.
arXiv:2607. 06799v1 Announce Type: cross Abstract: Evaluating uncertainty in AI-generated SQL queries requires estimating whether a query is correct, where correct means it executes to the same result as a human-written reference.
arXiv:2607. 07504v1 Announce Type: new Abstract: Product data scientists often ask LLM-based agents to help with recurring execution tasks such as cleaning data, writing SQL, choosing statistical tests, and formatting results.
arXiv:2607. 07507v1 Announce Type: cross Abstract: Hallucinations in vision language models (VLMs) are commonly treated as semantic errors, yet they often arise from partial or ambiguous visual evidence.
arXiv:2510. 13817v2 Announce Type: replace Abstract: The growth of IoT devices in shared environments has outpaced our ability to identify them, posing urgent risks to privacy, safety, and accountability.
arXiv:2607. 07391v1 Announce Type: new Abstract: Mathematical reasoning benchmarks typically provide all facts needed to solve each problem, while interactive benchmarks often mix reasoning with tools, retrieval, and long-horizon dialogue.