6 papers
Weight Ensembling Improves Reasoning in Language Models
Xingyu Dang, Christina Baek, Kaiyue Wen +2
We investigate a failure mode that arises during the training of reasoning models, where the diversity of generations begins to collapse, leading to suboptimal test-time scaling. N…
Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance
Sachin Goyal, Christina Baek, J. Zico Kolter +1
A standard practice when using large language models is for users to supplement their instruction with an input context containing new information for the model to process. However…
Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
Eungyeup Kim, Mingjie Sun, Christina Baek +2
Recently, Miller et al. (2021) and Baek et al. (2022) empirically demonstrated strong linear correlations between in-distribution (ID) versus out-of-distribution (OOD) accuracy and…
Predicting the Performance of Foundation Models via Agreement-on-the-Line
Rahul Saxena, Taeyoun Kim, Aman Mehra +3
Estimating the out-of-distribution performance in regimes where labels are scarce is critical to safely deploy foundation models. Recently, it was shown that ensembles of neural ne…
Why is SAM Robust to Label Noise?
Christina Baek, Zico Kolter, Aditi Raghunathan
Sharpness-Aware Minimization (SAM) is most known for achieving state-of the-art performances on natural image and language tasks. However, its most pronounced improvements (of tens…
Understanding Catastrophic Forgetting in Language Models via Implicit Inference
Suhas Kotha, Jacob Mitchell Springer, Aditi Raghunathan
We lack a systematic understanding of the effects of fine-tuning (via methods such as instruction-tuning or reinforcement learning from human feedback), particularly on tasks outsi…