In-Context Learning Without Copying
Induction heads are attention heads that perform inductive copying by matching patterns from earlier context and copying their continuations verbatim. As models develop induction heads, they experience a sharp drop in training loss, a phenomenon cited as evidence that induction heads may underlie a wide range of in-context learning (ICL) capabilities. In this work, we investigate whether induction heads are a necessary building block for learning abstractive ICL capabilities (i.e., tasks where the answer is not contained in the input context), or whether such capabilities can emerge independently. We propose Hapax, a training regime that omits the loss contribution of tokens predictable by induction heads. Despite a significant reduction in inductive copying, abstractive ICL capabilities are preserved, with the model achieving higher accuracy than the vanilla model on 13 out of 21 tasks, even though 31.7% of tokens are omitted from the loss. Furthermore, our model achieves lower loss values on token positions that induction heads cannot predict. Mechanistic analysis shows that models trained with Hapax develop fewer and weaker induction heads despite preserving abstractive ICL capabilities. Our findings suggest that the developmental link between induction heads and abstractive ICL capabilities is weaker than previously hypothesized.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Copy-Paste to Mitigate Large Language Model Hallucinations
While Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to generate contextually grounded responses, contextual faithfulness remains challenging as LLMs may not consistently trust provided context…
Context and Copying in Neural Machine Translation
Neural machine translation systems with subword vocabularies are capable of translating or copying unknown words. In this work, we show that they learn to copy words based on both the context in which the words appear as…
Machine TranslationTranslationLanguage Models "Grok" to Copy
We examine the pre-training dynamics of language models, focusing on their ability to copy text from preceding context--a fundamental skill for various LLM applications, including in-context learning (ICL) and retrieval-…
In-Context LearningLanguage ModellingRAGRetrieval-augmented GenerationMitigating Copy Bias in In-Context Learning through Neuron Pruning
Large language models (LLMs) have demonstrated impressive few-shot in-context learning (ICL) abilities. Still, we show that they are sometimes prone to a `copying bias', where they copy answers from provided examples ins…
In-Context LearningState Space ModelsRepeat After Me: Transformers are Better than State Space Models at Copying
Transformers are the dominant architecture for sequence modeling, but there is growing interest in models that use a fixed-size latent state that does not depend on the sequence length, which we refer to as "generalized …
State Space Models