arXiv AI
Aug 11
Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families
arXiv:2608. 08029v1 Announce Type: cross Abstract: Khatri et al.
Probe Choice Changes Canary-Memorization Verdicts: Three Post-Hoc Disagreement Case Studies in a Text-Dominant LoRA-Tuned Autoregressive Testbed
arXiv:2606. 31168v1 Announce Type: cross Abstract: We audit a fixed prefix-window mean-NLL memorization probe (K=20) on a Qwen2.
Related stories
arXiv AI
Jul 8
Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade
arXiv:2607. 06503v1 Announce Type: new Abstract: Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable.
arXiv Machine Learning
Jun 2
CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language Models
arXiv:2606. 01695v1 Announce Type: new Abstract: Adversaries can implant latent harmful behavior by poisoning as few as 1% of fine-tuning examples.
arXiv AI
Aug 19
Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations
The paper investigates whether the hidden activations of large language models (LLMs) contain signals about the vulnerability of C/C++ code when the code is provided as context. By extracting prefill token activations from four LLMs and training small MLP probes, the authors achieve an average F1 score of 41.7% across four benchmarks, with the best probe matching state‑of‑the‑art fine‑tuned classifiers on the Devign dataset. The results suggest that a coding LLM’s internal representation can inform vulnerability detection, opening the door to lightweight, model‑native screening methods.
arXiv AI
Jun 30
Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense
arXiv:2606. 29441v1 Announce Type: cross Abstract: Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists.
arXiv Machine Learning
Aug 14
Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection
arXiv:2608. 12652v1 Announce Type: cross Abstract: Benchmark contamination is diagnosed today with n-gram overlap, with likelihood-based membership inference, or with canary strings, and each needs something usually unavailable: the training corpus, a well-chosen test statistic, or foresight at dataset release.
arXiv AI
Jun 9
Strained Coherence: A Pre-Failure Signal in Coding Agent Execution Trajectories
arXiv:2606. 07889v1 Announce Type: cross Abstract: LLM-based coding agents sometimes acknowledge a problem in their own reasoning and then proceed anyway.
Hugging Face Trending Papers
Jun 28
Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense
Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists. We evaluate five defense paradigms (no defense, static steering, CAST, AlphaSteer, probe-gated) across seven instruction-tuned models (7-31B) and five attack types (GCG, AutoDAN, DeepInception, prefilling, intent laundering).
arXiv Machine Learning
Jul 13
Memory-Managed Long-Context Attention: Bounded Editable Memory with a Hard Lifecycle and Calibrated Sparse Fallback
arXiv:2606. 28876v2 Announce Type: replace-cross Abstract: We study memory-managed long-context attention: explicit bounded memory with a learned query-independent writer, lifecycle control, query-aware reading, calibrated sparse fallback, and frozen-LLM generation from raw evidence.
arXiv AI
Jul 24
SR-TTT Does Not Learn Retrieval: A Correction and Mechanistic Post-Mortem of Surprisal-Aware Residual Test-Time Training
arXiv:2603. 06642v2 Announce Type: replace-cross Abstract: Test-Time Training (TTT) language models replace the KV-cache with fast weights updated during inference, achieving O(1) memory but suffering catastrophic failure on exact-recall tasks.
arXiv AI
Jun 8
Endogenous Resistance to Activation Steering in Language Models
arXiv:2602. 06941v2 Announce Type: replace-cross Abstract: Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.
arXiv Machine Learning
Jun 29
Test-Input Generation for Tensor Programs: What Actually Finds Kernel Bugs
arXiv:2606. 27396v1 Announce Type: cross Abstract: Test-input generation for tensor kernels is folkloric.