The study investigates whether particular attention heads and individual neurons within those heads in language models are responsible for detecting network infrastructure information—specifically hostnames paired with IP addresses. Using causal ablation and selective testing across five models from three architecture families, the authors find that a small subset of heads reliably identifies such information with near-perfect accuracy. However, the extent to which this responsibility is concentrated in a single neuron varies by model; in some cases a single neuron suffices, while in others the signal is distributed across the head. The findings generalize to an independent reverse‑DNS dataset, though single‑neuron detectors are less robust.
By Abdul Kadir (University of Oldenburg, Oldenburg, Germany, German Research Center for Artificial Intelligence), Md Mohasin Hossain (German Research Center for Artificial Intelligence, Saarland University, Saarbrucken, Germany), Daniel Sonntag (University of Oldenburg, Oldenburg, Germany, German Research Center for Artificial Intelligence)
Ask a pretrained biomedical language model whether "cortisol 28 ug/dL" and "stock-market volatility" are related, and it returns a cosine similarity of 0. 83 on a scale where 1.
arXiv:2606. 09672v1 Announce Type: new Abstract: Ask a pretrained biomedical language model whether "cortisol 28 ug/dL" and "stock-market volatility" are related, and it returns a cosine similarity of 0.
By Suraj Biswas, Saurabh Gupta, Pritam Mukherjee
The study investigates the consistency and specificity of language model circuits across six tasks and five models, focusing on component-level (attention heads and MLP blocks) and neuron-level circuits. Component-level circuits are highly consistent and causally important but lack task specificity, as ablating a circuit for one task similarly harms performance on other tasks. Neuron-level circuits show higher task specificity but lower consistency, with overlap mainly between closely related tasks. The analysis of Llama‑3.2‑3B reveals that shared components are predominantly MLP blocks, while attention heads act as generic attention‑sink heads.
By Michael Li, Nishant Subramani
arXiv:2610.20179v1 Announce Type: cross
Abstract: Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot...
By Davide Baldelli, Robyn Kozierok, Mirko Bronzi, Damiano Fornasiere
arXiv:2608. 05624v1 Announce Type: new Abstract: Sycophantic responses are becoming pervasive in large language models (LLMs), and prior work has pointed out that some of them could be harmful.
By Bohan Jiang, Dawei Li, Yasin Silva, Huan Liu
Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot control what their activations encode. Humans can l...
arXiv:2608. 16347v1 Announce Type: cross Abstract: Direct communication between AI systems relies on natural language as an intermediate layer, incurring encoding/decoding overhead, token cost, and latency.
By Fernando Cardenas Piepereit
The paper evaluates nine on‑device named‑entity recognition models ranging from classical taggers to large language models, measuring not only accuracy but also latency and output validity. Using a silver‑gold benchmark derived from an LLM judge panel and a human‑validated corpus, the study shows that encoder‑based models achieve comparable accuracy to a 4 B instruct LLM while being much smaller, faster, and producing no malformed output. Confidence calibration of GLiNER is analyzed, revealing over‑confidence but improved reliability after temperature scaling and thresholding.
By Vinay Kumar Chaganti
arXiv:2607. 14111v1 Announce Type: cross Abstract: Can small language models detect and report on perturbations their own internal activations?
By Ely Hahami, Ishaan Sinha, Lavik Jain
The paper introduces a method for identifying the dominant knowledge source behind large language model (LLM) outputs, distinguishing between faithfulness violations (misuse of provided context) and factuality violations (errors in internal knowledge). A simple linear probe trained on hidden representations can reliably classify this source, and the authors present AttriWiki, a self‑supervised pipeline that generates labeled training data by prompting models to recall withheld entities or read them from context. Probes trained on AttriWiki achieve high Macro‑F1 scores across several models and datasets, generalize zero‑shot to a benchmark, and show that attribution mismatches can increase error rates by up to 70%.
"whyItMatters":"The study demonstrates that knowing the source of an LLM’s answer is crucial for effective mitigation of hallucinations, as attribution mismatches significantly raise error rates."
By Ivo Brink, Alexander Boer, Dennis Ulmer
arXiv:2607. 21692v1 Announce Type: new Abstract: Sparse attention reduces the cost of long contexts by allowing each query to read only selected parts of the input.
By Jim Allchin