AI/ML arXiv cs.AI

Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models

Develops a transparent SAE-feature steering pipeline for behavioral control in LLMs using a statistically grounded Borda consensus approach.

AI/ML arXiv cs.AI

Logic-Guided Data Extraction with Answer Set Programming and Large Language Models

Combines LLM-based data extraction with Answer Set Programming (ASP) to ensure logical consistency and reduce the number of LLM calls required for complex extraction tasks.

AI/ML arXiv cs.AI

Geometry-Guided Constraint Learning for LLM Safety Classification

Explores the use of Sparse Autoencoders (SAE) to optimize safety classification in LLMs, suggesting safety boundaries admit low-dimensional linear descriptions in SAE feature space.

AI/ML arXiv cs.AI

Rethinking Uncertainty Evaluation in Large Language Models

Critiques current uncertainty evaluation in LLMs, arguing that calibration is insufficient and proposing the C1 metrics to measure coherent probabilistic beliefs.

AI/ML arXiv cs.AI

Spectral-LSH: Sub-Quadratic Prompt Compression via Krylov-Projected Locality-Sensitive Hashing

Introduces Spectral-LSH, a training-free prompt compression method using Krylov-projected Locality-Sensitive Hashing to reduce prefill attention costs.

AI/ML arXiv cs.AI

Beyond Tracking or Shortcut: Composition-Bounded Predictive States in Poker Autoregressive Models

Analyzes opponent-range representation in poker autoregressive models, finding that most predictive information stems from visible betting patterns rather than hidden states.

Software Engineering Hacker News

git's –end-of-options Flag

Discussion regarding the use of the --end-of-options flag in git to explicitly separate options from positional arguments.

AI/ML arXiv cs.AI

FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads

FineServe introduces a multi-model LLM serving workload dataset and generator to better benchmark routing and scheduling in production environments.

AI/ML arXiv cs.AI

Hybrid LSTM-Graph Neural Framework for Robust Financial Fraud Detection and Adversarial Resilience

FraudShield AI is a hybrid LSTM-Graph Neural framework designed to detect sophisticated financial fraud by combining temporal sequences and relational context.

AI/ML arXiv cs.AI

OpenEvoShield: Dual Non-Stationary Continual Defense for Open-World Multi-Agent System Attacks

OpenEvoShield is a co-evolutionary continual defense framework designed to protect multi-agent LLM systems from dynamic adversarial attacks.

Hardware/Chips arXiv cs.AI

Benchmarking Confidential GPU Inference on NVIDIA H100 under Intel TDX

A benchmark study on the performance overhead of confidential GPU inference using NVIDIA H100 GPUs under Intel TDX.

AI/ML arXiv cs.AI

FormulaSPIN: Self-Play Fine-Tuning for Natural Language to Spreadsheet Formula Generation

FormulaSPIN introduces a self-play fine-tuning framework that improves natural language to spreadsheet formula generation without additional data.

AI/ML arXiv cs.AI

Information Discernment in Large Language Models

The Learn2Discern (L2D) framework reveals that LLMs struggle with source and truth discernment when integrating external knowledge.

AI/ML arXiv cs.AI

NEXUS: Structured Runtime Safety for Tool-Using LLM Agents

NEXUS is a structured runtime safety monitor for tool-using LLM agents that uses a graded escalation policy to block or revise risky actions.

AI/ML arXiv cs.AI

Stochastic Primal-Dual Decoding for Multiobjective Generative Recommender Systems

A new stochastic primal-dual decoding layer for generative recommender systems to balance relevance with multi-objective constraints at inference time.

AI/ML arXiv cs.AI

LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning

LISA is a plug-and-play attention replacement module that reduces inference complexity from O(n^2) to O(nM) for long-context reasoning models.

AI/ML arXiv cs.AI

Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality

A study isolates the impact of 'agent harnesses' (middleware) on coding agent quality, finding that rapid iterations in the harness can cause significant regressions regardless of the underlying LLM.

AI/ML arXiv cs.AI

Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding

The Auto-AEG pipeline enables scalable data construction for open-vocabulary audio event grounding, introducing the AEGBench dataset for evaluating temporal localization in LALMs.

AI/ML arXiv cs.AI

Human Grounded Evaluation of Large Language Models for Optical Network Automation

HuGLEN is introduced as a stepwise evaluation pipeline that combines LLM-as-a-judge with expert ratings to optimize the trade-off between quality and efficiency for network automation.

AI/ML arXiv cs.AI

Enhancing Rubric-based RL via Self-Distillation

The CriPO method enhances rubric-based RL through on-policy self-distillation to solve exploration failures (unexplored and suppressed criteria) in LLM training.