Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance
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, models struggle to reliably follow the input context, especially when it conflicts with their parametric knowledge from pretraining. In-principle, one would expect models to adapt to the user context better after instruction finetuning, particularly when handling knowledge conflicts. However, we observe a surprising failure mode: during instruction tuning, the context reliance under knowledge conflicts initially increases as expected, but then gradually decreases as instruction finetuning progresses. This happens while the performance on standard benchmarks keeps on increasing far after this drop. We call this phenomenon context-parametric inversion and observe it across multiple general purpose instruction tuning datasets such as TULU, Alpaca and Ultrachat, across different model families like Llama, Mistral, and Pythia. We perform various controlled studies and theoretical analysis to show that context-parametric inversion occurs due to examples in the instruction finetuning data where the input context provides information that aligns with model's parametric knowledge. Our analysis suggests some natural mitigation strategies with limited but insightful gains, and serves as a useful starting point in addressing this deficiency in instruction finetuning.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Updating Parametric Knowledge with Context Distillation Retains Post-Training Capabilities
Post-training endows pretrained LLMs with a variety of desirable skills, including instruction-following, reasoning, and others. However, these post-trained LLMs only encode knowledge up to a cut-off date, necessitating …
Instruction Tuned Models are Quick Learners
Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a pleth…
In-Context LearningMulti-Task LearningQuestion RewritingTransfer LearningMixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models
Sparse Mixture-of-Experts (MoE) is a neural architecture design that can be utilized to add learnable parameters to Large Language Models (LLMs) without increasing inference cost. Instruction tuning is a technique for tr…
Mixture-of-ExpertsZero-shot GeneralizationDiffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
The recent surge of generative AI has been fueled by the generative power of diffusion probabilistic models and the scalable capabilities of large language models. Despite their potential, it remains elusive whether diff…
In-Context LearningLanguage ModelingLanguage ModellingMasked Language ModelingSteering Large Language Models for Machine Translation with Finetuning and In-Context Learning
Large language models (LLMs) are a promising avenue for machine translation (MT). However, current LLM-based MT systems are brittle: their effectiveness highly depends on the choice of few-shot examples and they often re…
In-Context LearningMachine TranslationTranslation