Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2609.39972v1 Announce Type: new Abstract: Speculative decoding accelerates language model inference by verifying multiple draft tokens in a single target-model pass. Recent parallel drafters ha...
arXiv:2609.40097v1 Announce Type: new Abstract: Existing auto-research benchmarks often entangle multiple sources of improvement, including training frameworks, hyperparameters, compute budgets, and...
arXiv:2609.40124v1 Announce Type: new Abstract: Bias has long been studied in social psychology and cognitive science, where decades of research have produced a body of validated interventions that r...
SCB: SpeechConversationBench (SCB) evaluates multi-turn reasoning in speech-to-speech models by using 103 sharded GSM8K mathematical problems. The benchmark compares three delivery modes: a full single-turn problem, a concatenated multi-shard version, and an incremental spoken disclosure across turns. Results show that sharded accuracy drops by 5.0–25.3 percentage points for four commercial systems, while the internal LEGO pipeline maintains 77.5% accuracy across all conditions, outperforming GPT‑4o Realtime’s 76.6% sharded accuracy.
The paper introduces the problem of cross‑lingual loopholes in large language model (LLM) unlearning, where forgetting a fact in one language can leave it accessible in others. It presents a new 174‑language benchmark, the Cross‑Lingual Unlearning Tensor, and proposes COVER, a method that selects a subset of source languages to maximize unlearning coverage under a language budget. Experiments show COVER reduces residual knowledge by 7.8–27.3% compared to uniform selection and works on both synthetic and real low‑resource news data.
arXiv:2609.40340v1 Announce Type: new Abstract: Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents...
arXiv:2609.38324v1 Announce Type: cross Abstract: Multi-agent systems of LLMs add discussion to majority voting and are therefore expected to be more capable. However, empirical reports conflict on w...
arXiv:2609.38385v1 Announce Type: new Abstract: Supervised fine-tuning of discrete diffusion language models masks some response tokens and trains the model to recover their original values from the...
arXiv:2609.38426v1 Announce Type: cross Abstract: We introduce LoopVL to study whether Loop Transformers can be effectively extended to vision- language models. LoopVL combines Module-Loop and Model-...
arXiv:2609.38448v1 Announce Type: new Abstract: Open-ended LLM homogeneity can create false plurality when several systems appear to offer independent perspectives while returning the same familiar d...
arXiv:2609.38574v1 Announce Type: new Abstract: Large language models are frequently proposed as a route to AI-powered services for African communities, but they are least reliable exactly where the...
arXiv:2609.38722v1 Announce Type: cross Abstract: LLM watermarking has become an effective approach to distinguishing AI-generated text from human-written text by embedding detectable patterns during...
The paper introduces a Voice Retention / Representation Ratio metric to assess bias in large language model (LLM) summaries of employee feedback. Using a bilingual corpus of 2,586 responses from a global professional services firm, the study finds that criticism is reported more reliably than praise, and that LLM summaries tend to filter by popularity rather than sentiment—criticism often survives while single-mention concerns, short or German-only content are frequently omitted. The authors argue that prevalence, not sentiment, drives the bias, and provide a metric, field evidence, and a disaggregated voice‑retention card for future audits.
arXiv:2609.39050v1 Announce Type: cross Abstract: As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern. Prior work has e...
arXiv:2609.39334v1 Announce Type: cross Abstract: Test-time scaling has recently emerged as a powerful approach for improving LLM reasoning by allocating additional computation during inference, subs...
arXiv:2609.39549v1 Announce Type: cross Abstract: As Large Language Model (LLM) agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant secu...
The paper introduces FIGS, a dual‑axis evaluation framework for multi‑turn sycophancy that avoids penalizing empathy. It uses a 10‑turn conversational simulator with 500 diverse scenarios to test whether models stay truthful while keeping praise proportional, and whether they show calibrated validation of user feelings. The study finds that current models either drift toward sycophancy or become overly detached, highlighting an unresolved trade‑off in sustained dialogue.
arXiv:2609.39920v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) exhibit strong multimodal in-context learning (ICL) capabilities, yet this ability degrades substantially as mod...
arXiv:2510.13935v3 Announce Type: replace-cross Abstract: The facts a language model stores are tied to its parameter count, so small models that fit on edge devices fail on expert problems, which ne...
arXiv:2601.09717v2 Announce Type: replace-cross Abstract: Online medical consultations contain sensitive health information whose privacy implications depend not only on the entities mentioned but al...