Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2609.15561v1 Announce Type: new Abstract: Evaluating the factual correctness of large language models (LLMs) is vital for many applications. But are our evaluation tools themselves trustworthy?...
arXiv:2609.15654v1 Announce Type: new Abstract: Activation steering has been used to control traits such as honesty, refusal, and sycophancy, yet supportive empathy is evaluated along multiple dimens...
arXiv:2609.15684v1 Announce Type: new Abstract: Language agents increasingly rely on reusable skills, but post-failure repair is often handled by opaque one-shot reflection: a model generates a skill...
arXiv:2609.15743v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems, trained on paired speech-text data, have been improved by leveraging language models (LMs) trained on text-...
arXiv:2609.15851v1 Announce Type: new Abstract: Language models can learn from experience, but raw solution trajectories are often too long and noisy to provide effective guidance. In this work, we p...
arXiv:2609.15886v1 Announce Type: new Abstract: Large language models (LLMs) often learn both desirable and undesirable properties during post-training. We study whether midtraining, an earlier train...
arXiv:2609.15964v1 Announce Type: new Abstract: Large language models (LLMs) have been widely adopted for clinical question answering (QA). Current systems can attach citations to their answers, but...
The paper discusses the use of synthetic data in marketing research, arguing that the key question is not whether synthetic respondents work, but when they do. It categorizes synthetic data into three types—ungrounded LLM responses, segment-level personas, and individual-level digital twins—and maps each to the decisions they can support. The authors also propose a taxonomy of accuracy measures, highlight the forgotten question problem, and introduce an ex‑ante answerability diagnostic based on R² to improve twin-human correlation.
arXiv:2609.13291v1 Announce Type: cross Abstract: We present ScorePrompts, an interactive system in which users upload a score, receive natural-language descriptions of its musical structure, ask que...
arXiv:2609.15364v1 Announce Type: new Abstract: Digital agents must often adapt to new environments whose interfaces, tools, and failure modes are not fully captured by pretrained models. We introduc...
arXiv:2609.13486v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning decoder-only large language models (LLMs) for retrieval yields strong first-stage retrievers, with effectivene...
arXiv:2512.09944v4 Announce Type: replace Abstract: Echocardiography interpretation requires integrating multi-view temporal evidence with quantitative measurements and guideline-grounded reasoning,...
NoteVQA is a new benchmark that collects 252 real‑life visual questions from the Chinese image‑sharing platform Xiaohongshu, covering 12 topics and 7 user intents. Each question is paired with a concise expert reference and a human‑audited interleaved answer that blends text and visual evidence. The study evaluates VLMs on short‑answer correctness and interleaved answer quality using a new AgenticInterleave framework and a 12‑dimensional IVR‑12 rubric, finding that even state‑of‑the‑art models achieve only about 53% accuracy and lag behind human references in content quality.
arXiv:2609.14666v1 Announce Type: cross Abstract: Turn-taking is a fundamental component of spoken interaction, and while humans naturally rely on both verbal and non-verbal signals, dialogue systems...
The paper evaluates eleven vision‑language models (VLMs) for extracting structured fields from business documents, focusing on robustness, cost, and governance rather than just accuracy. Using a held‑out set of 750 synthetic checks, the study finds that fine‑tuning open‑source VLMs on 3,000 samples yields an F1 score above 0.98, surpassing all zero‑shot commercial systems, while GPT‑5 tops the commercial group and Claude Sonnet 4.5 fails on date extraction. The authors also present a practitioner‑oriented selection framework that maps task profiles—such as quality, latency, governance, and volume—to recommended approaches via filtering and total‑cost minimization, demonstrated on a mid‑volume document‑extraction scenario.
arXiv:2609.14758v1 Announce Type: cross Abstract: Tool-augmented language models are evaluated on whether they reach the right answer, not on whether they report honestly when a tool fails to supply...
arXiv:2609.15408v1 Announce Type: cross Abstract: Long-video understanding remains challenging for multimodal large language models (MLLMs) because densely encoding long frame sequences is computatio...
arXiv:2609.15640v1 Announce Type: cross Abstract: Long-text image--text congruence scoring is increasingly important for vision-language systems that must evaluate whether detailed textual descriptio...
arXiv:2609.15660v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) grounds a language model's answers on retrieved external knowledge and returns each answer with citations that i...
arXiv:2404.00727v3 Announce Type: replace Abstract: All state-of-the-art coreference resolution (CR) models involve finetuning a pretrained language model. Whether the superior performance of one CR...