anchor
Findings
- IC-1015GPT-J and 10 other LLMs exhibit overthinking: calibrated accuracy given incorrect few-shot demonstrations peaks at a critical layer then declines, and ablating 5 false induction heads in late layers reduces the accuracy gap by 38.9% on average [eval]
- IC-1088ICL predictions in LLaMA, LLaMA-2, and Falcon models depend on in-context label information and can learn truly novel label relationships [eval]
- IC-1089ICL in LLaMA, LLaMA-2, and Falcon models cannot fully overcome pre-training label preferences when in-context labels are flipped [eval]
- IC-327Llama-3-8B-Instruct, Mistral-7B-Instruct-v0.3, and several other LLMs produce well-calibrated verbal confidence estimates on classification tasks [eval]
- IC-348Sequential parameter-modifying editing causes progressive degradation of general abilities in GPT-2 XL, Llama-2 7B, and Llama-3 8B, driven by growth in the condition number of the edited matrix [eval]
- IC-349Larger LLMs (Llama-2 7B, Llama-3 8B) suffer more severe general ability degradation than smaller models (GPT-2 XL 1.5B) under the same number of sequential edits [eval]
- IC-350Editing conceptual knowledge with rome on Llama-2 7B is harder than factual knowledge editing, with the model failing to update concept-instance relationships [eval]
- IC-401Ablating safety attention heads minimally degrades helpfulness on zero-shot tasks and also impairs course-correction capability in Llama-2-7b-chat [eval]