558 citations · 3.6k across the 65 of their papers we have counts for
69 papers
Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations
Yanda Chen, Ruiqi Zhong, Narutatsu Ri +5
Large language models (LLMs) are trained to imitate humans to explain human decisions. However, do LLMs explain themselves? Can they help humans build mental models of how LLMs pro…
Jailbroken: How Does LLM Safety Training Fail?
Alexander Wei, Nika Haghtalab, Jacob Steinhardt
Large language models trained for safety and harmlessness remain susceptible to adversarial misuse, as evidenced by the prevalence of "jailbreak" attacks on early releases of ChatG…
Overthinking the Truth: Understanding how Language Models Process False Demonstrations
Danny Halawi, Jean-Stanislas Denain, Jacob Steinhardt
Modern language models can imitate complex patterns through few-shot learning, enabling them to complete challenging tasks without fine-tuning. However, imitation can also lead mod…
Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
Yongyi Yang, Jacob Steinhardt, Wei Hu
Recent work has observed an intriguing ''Neural Collapse'' phenomenon in well-trained neural networks, where the last-layer representations of training samples with the same label…
Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition
Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt +1
As the scale of machine learning models increases, trends such as scaling laws anticipate consistent downstream improvements in predictive accuracy. However, these trends take the…
Mass-Producing Failures of Multimodal Systems with Language Models
Shengbang Tong, Erik Jones, Jacob Steinhardt
Deployed multimodal systems can fail in ways that evaluators did not anticipate. In order to find these failures before deployment, we introduce MultiMon, a system that automatical…