25 citations · 25 across the 5 of their papers we have counts for
6 papers
FidelityQ: Preserving Predictive Fidelity in Ultra-Low-Bit Language Model Quantization
Yujie Chen, Weiyan Zheng, Yiwu Yao +7
Ultra-low-bit scalar quantization offers a regular arithmetic structure for efficient deployment of large language models, but preserving predictive behavior at extreme precision r…
Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values
Jan Betley, Johannes Treutlein, Jan Dubiński +5
People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: the information they provide is influenc…
Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors
Maxime Riché, Daniel Tan, Vili Kohonen +1
Inoculation prompting is a selective-generalization technique used against Emergent Misalignment. We introduce inoculation adapters (IA), a family of methods that similarly reduce…
Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
Daniel Tan, Anders Woodruff, Niels Warncke +4
Language model finetuning often results in learning undesirable traits in combination with desired ones. To address this, we propose inoculation prompting: modifying finetuning dat…
Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
Narmeen Oozeer, Luke Marks, Shreyans Jain +2
Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of…
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
Jan Betley, Daniel Tan, Niels Warncke +5
We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting mode…