arXiv AI
LEMON: Equivariant Learning over Attention Maps for Zero-Shot Misbehavior Monitoring on New LLMs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 31
DARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging
The paper introduces DARTS, a method for tuning decoder representations during model merging. It addresses representation bias in autoregressive decoders by using an entropy‑weighted L1 loss and a per‑position additive bias to correct errors that accumulate across token positions. Experiments on code generation, mathematical reasoning, and instruction following with Llama‑2‑7B show that DARTS improves performance over standard surgery while adding only 0.1% extra parameters.
arXiv AI
Oct 15
Attention Sinks in VLMs Are Borrowed, Not Seen
arXiv:2610.15855v1 Announce Type: new Abstract: We study how to detect and mitigate visual attention sinks in vision-language models (VLMs). Visual attention sinks are image tokens that absorb a larg...
arXiv Machine Learning
Oct 5
Teaching LLMs to See Graphs: Unifying Text and Structural Reasoning
arXiv:2605.10247v2 Announce Type: replace Abstract: Applying Large Language Models (LLMs) to graph-structured data usually involves multi-step pipelines in which textual node attributes are compresse...
arXiv Machine Learning
Aug 12
UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations
arXiv:2608. 10835v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input.
arXiv Machine Learning
Jun 3
When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models
arXiv:2606. 03712v1 Announce Type: new Abstract: Graph Language Models (GLMs) have become a promising direction for adapting Large Language Models (LLMs) to graph learning tasks.
arXiv Machine Learning
Aug 7
Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language
arXiv:2608. 05238v1 Announce Type: new Abstract: Training multimodal models to align time series with language runs into a self-supervision trap.