5 citations · 15 across the 18 of their papers we have counts for
5 papers · 1 filter
Effectiveness of Hidden-State Probes for Localizing Reasoning Failures
Shubham Subhnil, Yannis Belkhiter, Erik Miehling +2
Verifying the final answer of a long reasoning trace may show that the trace is wrong but it does not distinguish three cases. The problem may lie beyond the model's capability, an…
Local Causal Attribution of Chain-of-Thought Reasoning
Dennis Wei, Yannis Belkhiter, Erik Miehling +1
Understanding the causal structure of a language model's thought process is a problem of significant importance for both transparency and safety. In this work, we take a local appr…
The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Models
Matthew Riemer, Erik Miehling, Miao Liu +2
Although parameter-efficient fine-tuning methods, such as LoRA, only modify a small subset of parameters, they can have a significant impact on the model. Our instruction-tuning ex…
Programming Refusal with Conditional Activation Steering
Bruce W. Lee, Inkit Padhi, Karthikeyan Natesan Ramamurthy +4
LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscrimina…
Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor +35
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (trai…