Daily, Monday 14 April 2025
Reconstructed on 19 November 2026 from archived source metadata.
From the editor
The editor's note for this issue is not available. The developments below were selected and ranked automatically from the sources listed.
Top developments
- 1
The Structural Safety Generalization Problem
LLM jailbreaks are a widespread safety challenge. Given this problem has not yet been tractable, we suggest targeting a key failure mechanism: the failure of safety to generalize across semantically equivalent inputs. We further focus the target by requiring desirable…
- 2
Mitigating Many-Shot Jailbreaking
Many-shot jailbreaking (MSJ) is an adversarial technique that exploits the long context windows of modern LLMs to circumvent model safety training by including in the prompt many examples of a "fake" assistant responding inappropriately before the final request. With enough…
- 3
ControlNET: A Firewall for RAG-based LLM System
Retrieval-Augmented Generation (RAG) has significantly enhanced the factual accuracy and domain adaptability of Large Language Models (LLMs). This advancement has enabled their widespread deployment across sensitive domains such as healthcare, finance, and enterprise…
Further reading, by topic
This edition
6 developments and 0 advisories in the window. Selection and order are automatic: how stories are placed and ranked.