arXiv AI
Jul 7
The Anatomy of Uncertainty in LLMs
arXiv:2603. 24967v2 Announce Type: replace Abstract: Understanding why a large language model (LLM) is uncertain about the response is important for their reliable deployment.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Jul 7
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
arXiv:2607. 05365v1 Announce Type: cross Abstract: Streaming speech-to-speech language models aim to answer spoken queries directly with synthetic speech.
arXiv AI
Jul 7
Agent Step Value: State-Transition Measurement with State-Grounded LLM Evaluators
arXiv:2607. 04419v1 Announce Type: new Abstract: Most agent evaluations collapse a multi-step trace into a final answer, a success flag, or a trajectory-level score.
arXiv AI
Jul 7
VERITAS: Towards a General-Purpose Replication Tool for Scientific Research
arXiv:2607. 02931v1 Announce Type: new Abstract: AI tools are accelerating scientific publication while the systems that review it struggle to keep up, and independent verification of published research has become both harder and more important.
arXiv AI
Jul 7
RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents
arXiv:2607. 04713v1 Announce Type: cross Abstract: Reinforcement learning holds significant potential for training large language models (LLMs) to handle multi-turn interactive tasks.
arXiv AI
Jul 7
Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process
arXiv:2607. 03748v1 Announce Type: new Abstract: Unified multi-modal models (UMMs) have shown promising interleaved text-image reasoning capabilities, yet effectively optimizing such multi-turn generation via reinforcement learning (RL) remains an open challenge.
arXiv AI
Jul 7
Specific Domain Ontology Construction Using Large Language Models
arXiv:2606. 20691v1 Announce Type: cross Abstract: Ontologies are useful structures to organize and maintain information that can be understood both by humans and systems.
arXiv AI
Jul 7
Detecting Answer-Driven Reasoning in LLM-Based Educational Tutors via Truncated Chain-of-Thought Auditing
arXiv:2607. 04572v1 Announce Type: new Abstract: Large language model (LLM) tutors often produce fluent step-by-step explanations, but a correct and pedagogically formatted response does not guarantee that the answer was derived from the student-facing problem.
arXiv AI
Jul 7
JavaVulBench: A Java Vulnerability Benchmark with Realistic Splits, a Unified Multi-Backend Harness, and a Leakage-Aware Evaluation Mode
arXiv:2607. 02825v1 Announce Type: cross Abstract: We release \textsc{JavaVulBench}, a benchmark dataset and evaluation harness for Java vulnerability detection.
arXiv AI
Jul 7
HAS-Bench: Evaluating LLM-Based Human-Agent Systems under Configurable Human Participation
arXiv:2607. 04329v1 Announce Type: new Abstract: Large language models increasingly operate in settings where humans are active collaborators rather than passive task providers.
arXiv AI
Jul 7
Shortcut Learning in Legal Judgment Prediction: Empirical Evidence from the UK Employment Tribunal
arXiv:2607. 04261v1 Announce Type: new Abstract: Current Legal Judgment Prediction (LJP) is constrained by its reliance on post-hoc judicial materials, increasing the likelihood that models perform retrospective classification rather than true forecasting.
arXiv AI
Jul 7
Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents
arXiv:2607. 04528v1 Announce Type: new Abstract: Software-agent benchmarks usually report whether an agent solves a task, but the agent reaches that outcome through a harness that controls what it sees, which actions it can take, which failures are repaired, which states are verified, and which evidence is logged.
arXiv AI
Jul 7
SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
arXiv:2602. 06358v3 Announce Type: replace-cross Abstract: We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapters for large language models (LLMs).
arXiv AI
Jul 7
A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
arXiv:2607. 04574v1 Announce Type: cross Abstract: For LLM agents, supervised fine-tuning is not only about teacher labels' quality, but also about which interaction contexts those labels condition on.
arXiv Machine Learning
Jul 7
How Much of the Routing Gap Is Real? Decomposing the Router-to-Oracle Gap into Reproducible Specialist Advantage and Single-Draw Label Noise
arXiv:2607. 03436v1 Announce Type: new Abstract: Routing among large language models (LLMs) promises better quality at lower cost, motivated by the reported gap between learned routers and a per-instance oracle.
arXiv AI
Jul 7
Wan-Streamer v0.2: Higher Resolution, Same Latency
arXiv:2607. 04443v1 Announce Type: cross Abstract: We present Wan-Streamer v0.
arXiv AI
Jul 7
Knowledge-Centric Information Systems
arXiv:2607. 02609v1 Announce Type: cross Abstract: For decades, data engineering has developed mature architectural principles for integrating, governing, validating, cataloging, and serving organizational data.
arXiv Machine Learning
Jul 7
Toward Efficient Uncertainty in LLMs through Evidential Knowledge Distillation
arXiv:2507. 18366v2 Announce Type: replace Abstract: Accurate uncertainty quantification remains a key challenge for standard LLMs, prompting the adoption of Bayesian and ensemble-based methods.
arXiv AI
Jul 7
The Rise of Verbal Tics in Large Language Models: A Systematic Analysis Across Frontier Models
arXiv:2604. 19139v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) continue to evolve through alignment techniques such as Reinforcement Learning from Human Feedback (RLHF) and Constitutional AI, a growing and increasingly conspicuous phenomenon has emerged: the proliferation of verbal tics--repetitive, formulaic linguistic patterns that pervade model outputs.
arXiv AI
Jul 7
Empirical Computation: Prompting versus Programming
arXiv:2503. 10954v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents can solve *any* computational problem *without* an algorithm in a runtime *independent* of the computational complexity of that problem.