arXiv AI
TRACE: Temporal Risk Assessment and Concept Editing for Safer Language Generation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
4d ago
DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment
Safety alignment teaches language models to refuse harmful requests, yet the internal accessibility of hazardous concepts can retain traces of earlier training. Can checkpoints with equally safe behav...
arXiv AI
Jun 30
Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation
arXiv:2511. 05852v4 Announce Type: replace-cross Abstract: Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs).
arXiv Computation and Language
Sep 18
The Role of Fine-grained Harm Signals in LLM Safety
The study investigates how category‑specific harmfulness signals, isolated by removing the shared general harmfulness component, influence large language model (LLM) safety. Using activation steering across 11 risk categories in three instruction‑tuned LLMs, the authors find that the presence of harmfulness in these category residuals varies by category and that the pattern of inducing refusal is even more model‑dependent. Additionally, category residuals were shown to enhance the models’ downstream alignment with the shared general harmfulness representation, indicating that fine‑grained signals play a role beyond the general component.
arXiv AI
6d ago
Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs
The paper investigates how safety‑aligned large language models (LLMs) can still be tricked by jailbreaks or over‑refuse benign requests. By analyzing residual‑stream updates in decoder‑only Transformers, the authors find that harmfulness is more readily decoded from attention updates—especially in early layers—while the MLP component is primarily responsible for writing refusal responses. Post‑training enhances MLP‑driven refusal writing without improving harmfulness decodability, and causal interventions confirm that downstream MLP updates are crucial for the refusal shift caused by upstream attention changes. Building on these insights, the authors propose Sentinel, a system that combines an attention‑derived perception score with an MLP‑derived decision score to better detect jailbreaks and over‑refusals across multiple models.
arXiv AI
Aug 18
HarmProfile: Characterizing Harmful Distributions in Frontier LLMs
arXiv:2608. 14577v1 Announce Type: cross Abstract: Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis.
arXiv AI
Sep 24
Beyond Unsafe Detection: Counterfactually Anchored Evidence Attribution for Multi-Turn LLM Safety Failures
The paper introduces a counterfactually anchored evidence attribution approach for multi‑turn large language model safety failures. It presents a new dataset of 1,762 conversations, including adversarial, benign twins, and high‑risk vocabulary variants, and trains a lightweight hierarchical model that accurately predicts safety violations and attributes them to specific user turns and token spans. The model achieves high detection performance (F1 = 0.988) and significantly reduces adversarial confidence when top‑attributed tokens are removed, while maintaining low false‑positive rates on benign conversations.