How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations

• URL: http://arxiv.org/abs/2310.10616v1
• Date: Mon, 16 Oct 2023 17:40:49 GMT
• Title: How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations
• Authors: Tianyu Guo, Wei Hu, Song Mei, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai
• Abstract summary: This paper takes initial steps on understanding in-context learning (ICL) in more complex scenarios, by studying learning with representations. We construct synthetic in-context learning problems with a compositional structure, where the label depends on the input through a possibly complex but fixed representation function. We show theoretically the existence of transformers that approximately implement such algorithms with mild depth and size.
• Score: 98.7450564309923
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While large language models based on the transformer architecture have demonstrated remarkable in-context learning (ICL) capabilities, understandings of such capabilities are still in an early stage, where existing theory and mechanistic understanding focus mostly on simple scenarios such as learning simple function classes. This paper takes initial steps on understanding ICL in more complex scenarios, by studying learning with representations. Concretely, we construct synthetic in-context learning problems with a compositional structure, where the label depends on the input through a possibly complex but fixed representation function, composed with a linear function that differs in each instance. By construction, the optimal ICL algorithm first transforms the inputs by the representation function, and then performs linear ICL on top of the transformed dataset. We show theoretically the existence of transformers that approximately implement such algorithms with mild depth and size. Empirically, we find trained transformers consistently achieve near-optimal ICL performance in this setting, and exhibit the desired dissection where lower layers transforms the dataset and upper layers perform linear ICL. Through extensive probing and a new pasting experiment, we further reveal several mechanisms within the trained transformers, such as concrete copying behaviors on both the inputs and the representations, linear ICL capability of the upper layers alone, and a post-ICL representation selection mechanism in a harder mixture setting. These observed mechanisms align well with our theory and may shed light on how transformers perform ICL in more realistic scenarios.

Related papers

• How Do Nonlinear Transformers Learn and Generalize in In-Context Learning? [82.51626700527837]
  Transformer-based large language models displayed impressive in-context learning capabilities, where a pre-trained model can handle new tasks without fine-tuning. We analyze how the mechanics of how Transformer to achieve ICL contribute to the technical challenges of the training problems in Transformers.
  arXiv  Detail & Related papers  (2024-02-23T21:07:20Z)
• Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings [60.698130703909804]
  Transformers generalize to novel compositions of structures and entities after being trained on a complex dataset. We propose SQ-Transformer that explicitly encourages systematicity in the embeddings and attention layers. We show that SQ-Transformer achieves stronger compositional generalization than the vanilla Transformer on multiple low-complexity semantic parsing and machine translation datasets.
  arXiv  Detail & Related papers  (2024-02-09T15:53:15Z)
• Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data [21.242708937367865]
  Large language models (LLMs) are powerful models that can learn concepts at the inference stage via in-context learning (ICL) This paper studies the role of each component in the transformer architecture and provides a theoretical understanding to explain the success of the architecture.
  arXiv  Detail & Related papers  (2024-02-01T16:39:45Z)
• Positional Information Matters for Invariant In-Context Learning: A Case Study of Simple Function Classes [39.08988313527199]
  In-context learning (ICL) refers to the ability of a model to condition on a few in-context demonstrations to generate the answer for a new query input. Despite the impressive ICL ability of LLMs, ICL in LLMs is sensitive to input demonstrations and limited to short context lengths.
  arXiv  Detail & Related papers  (2023-11-30T02:26:55Z)
• Schema-learning and rebinding as mechanisms of in-context learning and emergence [10.370506005311091]
  In-context learning (ICL) is one of the most powerful and most unexpected capabilities to emerge in recent transformer-based large language models (LLMs) We demonstrate that comparable ICL capabilities can be acquired by an alternative sequence prediction learning method using clone-structured causal graphs (CSCGs)
  arXiv  Detail & Related papers  (2023-06-16T00:29:19Z)
• Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection [88.23337313766353]
  This work first provides a comprehensive statistical theory for transformers to perform ICL. We show that transformers can implement a broad class of standard machine learning algorithms in context. A emphsingle transformer can adaptively select different base ICL algorithms.
  arXiv  Detail & Related papers  (2023-06-07T17:59:31Z)
• Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers [71.32827362323205]
  We propose a new class of linear Transformers calledLearner-Transformers (Learners) They incorporate a wide range of relative positional encoding mechanisms (RPEs) These include regular RPE techniques applied for sequential data, as well as novel RPEs operating on geometric data embedded in higher-dimensional Euclidean spaces.
  arXiv  Detail & Related papers  (2023-02-03T18:57:17Z)
• Learning Bounded Context-Free-Grammar via LSTM and the Transformer:Difference and Explanations [51.77000472945441]
  Long Short-Term Memory (LSTM) and Transformers are two popular neural architectures used for natural language processing tasks. In practice, it is often observed that Transformer models have better representation power than LSTM. We study such practical differences between LSTM and Transformer and propose an explanation based on their latent space decomposition patterns.
  arXiv  Detail & Related papers  (2021-12-16T19:56:44Z)

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.