PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning
Instruction tuning enhances the instruction following ability of large language models by finetuning with supervised instruction data. Previous work proposes in-context instruction tuning (ICIT) where specific positive or negative examples are incorporated into the prompt for better performance. In this work, we propose PACIT, a simple and effective in-context instruction tuning method, inspired by the pedagogical concept of desirable difficulty. The PACIT method unlocks the power of examples by encouraging the model to actively learn to grasp the distinctions between the positive and negative examples instead of merely reading. The model is expected to first verify the correctness of the provided example according to the task description, which is then set as the condition for generating a better response to the task instance. Our extensive experiments prove the effectiveness of PACIT, outperforming ICIT baseline on both in-domain and out-domain tasks up to 9.16 and 3.14 average ROUGE-L scores, respectively. Moreover, PACIT can notably enhance the performance of instruction tuning even when all positive and negative examples are generated with a self-instruct method.
Code (1)
Tasks
Instruction FollowingZero-shot GeneralizationSimilar Papers 제목 키워드 기반
Contextual Speech Recognition with Difficult Negative Training Examples
Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR co…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionParameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models
Scaling the capacity of language models has consistently proven to be a reliable approach for improving performance and unlocking new capabilities. Capacity can be primarily defined by two dimensions: the number of model…
Mixture-of-ExpertsUnlocking the Power of LLM Uncertainty for Active In-Context Example Selection
Large Language Models (LLMs) have shown remarkable performance across a wide range of downstream tasks. However, it is challenging for users to discern whether the responses of LLM are generated with certainty or are fab…
Active LearningIn-Context LearningInformativenessCross-lingual QA: A Key to Unlocking In-context Cross-lingual Performance
Multilingual large language models (MLLMs) have demonstrated significant cross-lingual capabilities through in-context learning. Existing approaches typically construct monolingual in-context examples, either in the sour…
Cross-Lingual TransferIn-Context LearningQuestion AnsweringProteus: Incremental Memory Activation for Long-Context Sequence Modeling
The quadratic cost of attention-based sequence models for long contexts has motivated a growing line of research on memory-based models that can compress context into a compact state. However, most existing memory models…