Daily, Monday 20 January 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
Can Safety Fine-Tuning Be More Principled? Lessons Learned from Cybersecurity
As LLMs develop increasingly advanced capabilities, there is an increased need to minimize the harm that could be caused to society by certain model outputs; hence, most LLMs have safety guardrails added, for example via fine-tuning. In this paper, we argue the position that…
- 2
Tell me about yourself: LLMs are aware of their learned behaviors
We study behavioral self-awareness -- an LLM's ability to articulate its behaviors without requiring in-context examples. We finetune LLMs on datasets that exhibit particular behaviors, such as (a) making high-risk economic decisions, and (b) outputting insecure code. Despite…
- 3
A Novel Pearson Correlation-Based Merging Algorithm for Robust Distributed Machine Learning with Heterogeneous Data
Federated learning faces significant challenges in scenarios with heterogeneous data distributions and adverse network conditions, such as delays, packet loss, and data poisoning attacks. This paper proposes a novel method based on the SCAFFOLD algorithm to improve the quality…
Further reading, by topic
This edition
4 developments and 0 advisories in the window. Selection and order are automatic: how stories are placed and ranked.