Task Vectors in In-Context Learning: Emergence, Formation, and Benefit

• URL: http://arxiv.org/abs/2501.09240v1
• Date: Thu, 16 Jan 2025 01:54:23 GMT
• Title: Task Vectors in In-Context Learning: Emergence, Formation, and Benefit
• Authors: Liu Yang, Ziqian Lin, Kangwook Lee, Dimitris Papailiopoulos, Robert Nowak,
• Abstract summary: We investigate the formation of task vectors in a controlled setting using models trained from scratch on synthetic datasets. Our findings confirm that task vectors naturally emerge under certain conditions, but the tasks may be relatively weakly and/or non-locally encoded within the model. To promote strong task vectors encoded at a prescribed location within the model, we propose an auxiliary training mechanism based on a task vector prompting loss.
• Score: 17.72043522825441
• License:
• Abstract: In-context learning is a remarkable capability of transformers, referring to their ability to adapt to specific tasks based on a short history or context. Previous research has found that task-specific information is locally encoded within models, though their emergence and functionality remain unclear due to opaque pre-training processes. In this work, we investigate the formation of task vectors in a controlled setting, using models trained from scratch on synthetic datasets. Our findings confirm that task vectors naturally emerge under certain conditions, but the tasks may be relatively weakly and/or non-locally encoded within the model. To promote strong task vectors encoded at a prescribed location within the model, we propose an auxiliary training mechanism based on a task vector prompting loss (TVP-loss). This method eliminates the need to search for task-correlated encodings within the trained model and demonstrably improves robustness and generalization.

Related papers

• Learning Task Representations from In-Context Learning [73.72066284711462]
  Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning. We introduce an automated formulation for encoding task information in ICL prompts as a function of attention heads. We show that our method's effectiveness stems from aligning the distribution of the last hidden state with that of an optimally performing in-context-learned model.
  arXiv  Detail & Related papers  (2025-02-08T00:16:44Z)
• In-context Learning in Presence of Spurious Correlations [8.055478206164105]
  We study the possibility of training an in-context learner for classification tasks involving spurious features. We find that the conventional approach of training in-context learners is susceptible to spurious features. We propose a novel technique to train such a learner for a given classification task.
  arXiv  Detail & Related papers  (2024-10-04T04:26:36Z)
• Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation [45.568230152488276]
  We consider explicitly generative modeling task distributions placed over task identifiers. We propose robustifying fast adaptation from adversarial training. This work has practical implications, particularly in dealing with task distribution shifts in meta-learning.
  arXiv  Detail & Related papers  (2024-07-28T16:23:55Z)
• Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach [87.8330887605381]
  We show how to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. We synthesize a task-specific query with a learnable and lightweight module, which is independent of the pre-trained model. Our method achieves state-of-the-art performance under memory constraints, showcasing its applicability in real-world situations.
  arXiv  Detail & Related papers  (2024-07-09T15:45:04Z)
• Finding Visual Task Vectors [74.67336516908776]
  Visual Prompting is a technique for teaching models to perform a visual task via in-context examples, without any additional training. We analyze the activations of MAE-VQGAN, a recent Visual Prompting model, and find task vectors, activations that encode task-specific information.
  arXiv  Detail & Related papers  (2024-04-08T17:59:46Z)
• Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration [17.27164535440641]
  Posterior sampling is a promising approach, but it requires Bayesian inference and dynamic programming. We show that even though partial models exclude relevant information from the environment, they can nevertheless lead to good policies.
  arXiv  Detail & Related papers  (2023-02-08T18:35:24Z)
• Editing Models with Task Arithmetic [69.97273155842966]
  Changing how pre-trained models behave is a common practice when developing machine learning systems. We build task vectors by subtracting the weights of a pre-trained model from the weights of the same model after fine-tuning on a task. We show that these task vectors can be modified and combined together through arithmetic operations such as negation and addition.
  arXiv  Detail & Related papers  (2022-12-08T05:50:53Z)
• Unveiling Transformers with LEGO: a synthetic reasoning task [23.535488809197787]
  We study how the transformer architecture learns to follow a chain of reasoning. In some data regime the trained transformer finds "shortcut" solutions to follow the chain of reasoning. We find that one can prevent such shortcut with appropriate architecture modification or careful data preparation.
  arXiv  Detail & Related papers  (2022-06-09T06:30:17Z)
• Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization [101.72755769194677]
  We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph. Our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks. Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks.
  arXiv  Detail & Related papers  (2022-05-25T10:44:25Z)
• Adaptive Task Sampling for Meta-Learning [79.61146834134459]
  Key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test time. We propose an adaptive task sampling method to improve the generalization performance.
  arXiv  Detail & Related papers  (2020-07-17T03:15:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.