7 citations · 7 across the 6 of their papers we have counts for
7 papers
Don't Inoculate Everything: Stratified Inoculation Prompting Narrows Backdoor Triggers and Preserves Desired Traits
Kajetan Dymkiewicz, Tim Farrelly, Adam Práda +8
Supervised fine-tuning can teach language models undesired behaviours alongside desired ones. Inoculation prompting (IP) aims to limit unwanted generalisation by requesting the und…
Training Deliberative Monitors for Black-Box Scheming Detection
Aditya Sinha, Akshat Naik, Victor Gillioz +5
As autonomous agents become more capable of performing real-world tasks, distinguishing scheming behavior from benign task pursuit may become a central AI control problem. Existing…
Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
Satchel Grant, Victor Gillioz, Jake Ward +1
Defensive training methods such as positive preventative steering (PPS) and inoculation prompting (IP) offer surprising results through seemingly similar processes: both add trait-…
Recontextualization Mitigates Specification Gaming without Modifying the Specification
Ariana Azarbal, Victor Gillioz, Vladimir Ivanov +6
Developers often struggle to specify correct training labels and rewards. Perhaps they don't need to. We propose recontextualization, which reduces how often language models "game"…
Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment
Nevan Wichers, Aram Ebtekar, Ariana Azarbal +8
Large language models are sometimes trained with imperfect oversight signals, leading to undesired behaviors such as reward hacking and sycophancy. Improving oversight quality can…
Spaiche: Extending State-of-the-Art ASR Models to Swiss German Dialects
Clement Sicard, Kajetan Pyszkowski, Victor Gillioz
Recent breakthroughs in NLP largely increased the presence of ASR systems in our daily lives. However, for many low-resource languages, ASR models still need to be improved due in…
EEGEyeNet: a Simultaneous Electroencephalography and Eye-tracking Dataset and Benchmark for Eye Movement Prediction
Ard Kastrati, Martyna Beata Płomecka, Damián Pascual +4
We present a new dataset and benchmark with the goal of advancing research in the intersection of brain activities and eye movements. Our dataset, EEGEyeNet, consists of simultaneo…