ConTinTin: Continual Learning from Task Instructions

By Wenpeng Yin, Jia Li, Caiming Xiong. 2022

37 citations recorded by the source corpus.

The mainstream machine learning paradigms for NLP often work with two underlying presumptions. First, the target task is predefined and static; a system merely needs to learn to solve it exclusively. Second, the supervision of a task mainly comes from a set of labeled examples. A question arises: how to build a system that can keep learning new tasks from their instructions?This work defines a new learning paradigm ConTinTin (Continual Learning from Task Instructions), in which a system should learn a sequence of new tasks one by one, each task is explained by a piece of textual instruction. The system is required to (i) generate the expected outputs of a new task by learning from its instruction, (ii) transfer the knowledge acquired from upstream tasks to help solve downstream tasks (i.e., forward-transfer), and (iii) retain or even improve the performance on earlier tasks after learning new tasks (i.e., backward-transfer). This new problem is studied on a stream of more than 60 tasks, each equipped with an instruction. Technically, our method InstructionSpeak contains two strategies that make full use of task instructions to improve forward-transfer and backward-transfer: one is to learn from negative outputs, the other is to re-visit instructions of previous tasks. To our knowledge, this is the first time to study ConTinTin in NLP. In addition to the problem formulation and our promising approach, this work also contributes to providing rich analyses for the community to better understand this novel learning problem.

Subfields: Natural Language Processing, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Reinforcement Learning

Citations in the corpus

OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization (2022, background): “Existing work also address continuous adaptation of language models by revisiting the instructions (Yin et al., 2022) or examples (Scialom et al.”
Self-Instruct: Aligning Language Models with Self-Generated Instructions (2022, background): “A series of works have found evidence that vanilla language models can be effective at following general language instructions if tuned with annotated “instructional” data – datasets containing language instructional commands and their desired outcome based on human judgement (Weller et al., 2020; M”
A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, methodology): “, instruction [109], such as PAGeR [415], ConTinTin [477] and ENTAILMENT [460].”
Continual Training of Language Models for Few-Shot Learning (2022, background): “Several researchers have studied this problem recently (An-toniou et al., 2020; Qin and Joty, 2021; Jin et al., 2021; Xia et al., 2021; Yin et al., 2022).”
Style Over Substance: Evaluation Biases for Large Language Models (2023, unknown): “It is found that instruction-tuned LLMs can significantly enhance their performance following general language instructions (Weller et al., 2020; Mishra et al., 2022; Wang et al., 2022b; Wei et al., 2022; Sanh et al., 2022; Ouyang et al., 2022; Parmar et al., 2022; Scialom et al., 2022; Chung et al.”