arXiv AI
Jul 21
Constrained Path Reasoning: Measuring When Committed Stages Earn Their Cost
arXiv:2607. 17240v1 Announce Type: new Abstract: When does a committed intermediate stage in an LLM reasoning pipeline earn its cost?
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 21
Beyond Semantic Equivalence: Logical Graphs for LLM Uncertainty Quantification
arXiv:2607. 16868v1 Announce Type: new Abstract: Large Language Models (LLMs) often produce confidently stated yet unreliable outputs, posing critical challenges for deployment in safety-sensitive applications.
arXiv AI
Jul 21
MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs
arXiv:2507. 20804v3 Announce Type: replace Abstract: Large Language Models (LLMs) suffer from hallucinations due to their static parametric knowledge.
arXiv AI
Jul 21
OrientSAM: Mitigating Camera-Centric Shortcut in Multimodal Spatial Reasoning via Orientation-Aware Spatial Alignment
arXiv:2607. 17657v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) still struggle with spatial reasoning that requires perspective transformation.
arXiv AI
Jul 21
DeLIVeR: Decomposed Learning for Information-grounded Veracity Recognition via Reinforced Knowledge Graph Exploration
arXiv:2607. 17935v1 Announce Type: cross Abstract: Automated fact-checking remains a challenge for Large Language Models (LLMs) due to "query brittleness" in traditional retrieval systems.
arXiv Machine Learning
Jul 21
Manifold-Constrained Hyper-Connections for Parameter-Efficient Finetuning
arXiv:2607. 18130v1 Announce Type: new Abstract: Most parameter-efficient finetuning (PEFT) methods adapt weights or activations, thus leaving one of the key Transformer components unchanged: residual connections.
arXiv Machine Learning
Jul 21
A Weisfeiler-Leman Characterization of Global-Attention Graph Transformers for Mixed-Integer Linear Programs
arXiv:2607. 17570v1 Announce Type: new Abstract: Graph foundation models (GFMs) with global attention are increasingly used to represent mixed-integer linear programs (MILPs), aiming to capture structure beyond the locality of standard graph neural networks.
arXiv AI
Jul 21
Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
arXiv:2607. 18100v1 Announce Type: new Abstract: Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable.
arXiv AI
Jul 21
SyriSign: A Parallel Corpus for Arabic Text to Syrian Arabic Sign Language Translation
arXiv:2603. 29219v2 Announce Type: replace-cross Abstract: Sign language is the primary approach of communication for the Deaf and Hard-of-Hearing (DHH) community.
arXiv Machine Learning
Jul 21
Explaining and Tuning Transformer-based LLMs in Arithmetic Tasks with Human Strategies
arXiv:2607. 17166v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) continue to achieve state-of-the-art performance across various natural language processing tasks.
arXiv AI
Jul 21
How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs?
arXiv:2607. 18114v1 Announce Type: cross Abstract: Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-shot example, or a fake prior assistant turn often flips an originally correct answer.
arXiv AI
Jul 21
LaT: LLM-as-Trainer for Multi-Task Vehicle Routing Solvers
arXiv:2607. 17708v1 Announce Type: new Abstract: Multi-task neural solvers aim to handle multiple Vehicle Routing Problem (VRP) variants within a unified model, avoiding separate training for each constraint combination.
arXiv Machine Learning
Jul 21
Perturbation is All You Need for Extrapolating Language Models
arXiv:2605. 04344v2 Announce Type: replace-cross Abstract: This paper develops a statistical theory of extrapolation for large language models, by reinterpreting them through pre-post-additive noise models.
arXiv Machine Learning
Jul 21
When Can You Debias an LLM Judge? Identifiability Limits, a Test, and Designs for Top-k Ranking
arXiv:2607. 02104v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise.
arXiv Machine Learning
Jul 21
Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation
arXiv:2604. 16197v2 Announce Type: replace Abstract: Data attribution and valuation are critical for understanding data-model synergy for Large Language Models (LLMs), yet existing gradient-based methods suffer from scalability challenges on LLMs.
arXiv Machine Learning
Jul 21
When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift
arXiv:2602. 14161v2 Announce Type: replace Abstract: Detecting prompt injection, jailbreak attacks, and harmful requests is critical for deploying LLM-based agents safely, yet current evaluation practices in this literature overestimate generalization.
arXiv Machine Learning
Jul 21
Patch Policy: Efficient Embodied Control via Dense Visual Representations
arXiv:2607. 18236v1 Announce Type: cross Abstract: Pretrained dense visual features from Vision Transformers (ViTs) are powerful yet have been underutilized in robot learning.
arXiv Machine Learning
Jul 21
An Adjoint-Sensitivity Framework for Lost-in-the-Middle Phenomena in Causal Residual Transformers
arXiv:2607. 17696v1 Announce Type: cross Abstract: We develop an adjoint-sensitivity framework for positional influence in causal residual Transformers and separate unconditional analytic results from conditional boundary-shape conclusions.
arXiv Machine Learning
Jul 21
Feature-Guided Diffusion for Non-Differentiable Inverse Rendering
arXiv:2607. 17411v1 Announce Type: cross Abstract: Inverse rendering is traditionally solved via differentiable renderers and gradient descent, which requires substantial problem-specific engineering and is prone to getting stuck in local minima due to ambiguities.
arXiv AI
Jul 21
SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling
arXiv:2607. 16252v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning (PEFT) method for large language models.