21 citations · 43 across the 17 of their papers we have counts for
7 papers · 1 filter
Eliciting Behaviors in Multi-Turn Conversations
Jing Huang, Shujian Zhang, Lun Wang +3
Identifying specific and often complex behaviors from large language models (LLMs) in conversational settings is crucial for their evaluation. Recent work proposes novel techniques…
Blackbox Model Provenance via Palimpsestic Membership Inference
Rohith Kuditipudi, Jing Huang, Sally Zhu +3
Suppose Alice trains an open-weight language model and Bob uses a blackbox derivative of Alice's model to produce text. Can Alice prove that Bob is using her model, either by query…
LLMs Encode Harmfulness and Refusal Separately
Jiachen Zhao, Jing Huang, Zhengxuan Wu +2
LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by…
Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors
Jing Huang, Junyi Tao, Thomas Icard +2
Interpretability research now offers a variety of techniques for identifying abstract internal mechanisms in neural networks. Can such techniques be used to predict how models will…
HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks
Jiuding Sun, Jing Huang, Sidharth Baskaran +4
Mechanistic interpretability has made great strides in identifying neural network features (e.g., directions in hidden activation space) that mediate concepts(e.g., the birth year…
MIB: A Mechanistic Interpretability Benchmark
Aaron Mueller, Atticus Geiger, Sarah Wiegreffe +20
How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretabili…
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
Zhengxuan Wu, Aryaman Arora, Atticus Geiger +5
Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability resea…