1 citations · 1 across the 4 of their papers we have counts for
5 papers
Last Translation Benchmark
Vilém Zouhar, Niyati Bafna, Mukund Choudhary +263
For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, stan…
Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards
Magnus Jørgenvåg, David Kaczér, Lasse Ruttert +3
Emergent misalignment (EM) is the surprising tendency of language models to become broadly misaligned after fine-tuning on narrowly misaligned examples. While EM has been extensive…
From Value Conditioning to Behavioral Shift: Lightweight Value Alignment of LLMs
Shangrui Nie, Florian Mai, David Kaczér +3
Large language models exhibit value-related preferences in their outputs, yet steering such behavior often requires large training datasets or paired preference annotations. In thi…
Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models
Mehdi Ali, Manuel Brack, Max Lübbering +15
High-quality multilingual training data is essential for effectively pretraining large language models (LLMs). Yet, the availability of suitable open-source multilingual datasets r…
Superalignment with Dynamic Human Values
Florian Mai, David Kaczér, Nicholas Kluge Corrêa +1
Two core challenges of alignment are 1) scalable oversight and 2) accounting for the dynamic nature of human values. While solutions like recursive reward modeling address 1), they…