Born a Transformer -- Always a Transformer?

• URL: http://arxiv.org/abs/2505.21785v2
• Date: Fri, 30 May 2025 10:27:46 GMT
• Title: Born a Transformer -- Always a Transformer?
• Authors: Yana Veitsman, Mayank Jobanputra, Yash Sarrof, Aleksandra Bakalova, Vera Demberg, Ellie Pavlick, Michael Hahn,
• Abstract summary: We study a family of $textitretrieval$ and $textitcopying$ tasks inspired by Liu et al.<n>We observe an $textitinduction-versus-anti-induction$ asymmetry, where pretrained models are better at retrieving tokens to the right (induction) than the left (anti-induction) of a query token.<n>Mechanistic analysis reveals that this asymmetry is connected to the differences in the strength of induction versus anti-induction circuits within pretrained transformers.
• Score: 57.37263095476691
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformers have theoretical limitations in modeling certain sequence-to-sequence tasks, yet it remains largely unclear if these limitations play a role in large-scale pretrained LLMs, or whether LLMs might effectively overcome these constraints in practice due to the scale of both the models themselves and their pretraining data. We explore how these architectural constraints manifest after pretraining, by studying a family of $\textit{retrieval}$ and $\textit{copying}$ tasks inspired by Liu et al. [2024a]. We use a recently proposed framework for studying length generalization [Huang et al., 2025] to provide guarantees for each of our settings. Empirically, we observe an $\textit{induction-versus-anti-induction}$ asymmetry, where pretrained models are better at retrieving tokens to the right (induction) rather than the left (anti-induction) of a query token. This asymmetry disappears upon targeted fine-tuning if length-generalization is guaranteed by theory. Mechanistic analysis reveals that this asymmetry is connected to the differences in the strength of induction versus anti-induction circuits within pretrained transformers. We validate our findings through practical experiments on real-world tasks demonstrating reliability risks. Our results highlight that pretraining selectively enhances certain transformer capabilities, but does not overcome fundamental length-generalization limits.

Related papers

• Transformers Don't In-Context Learn Least Squares Regression [5.648229654902264]
  In-context learning (ICL) has emerged as a powerful capability of large pretrained transformers.<n>We study how transformers implement learning at inference time.<n>We highlight the role of the pretraining corpus in shaping ICL behaviour.
  arXiv  Detail & Related papers  (2025-07-13T01:09:26Z)
• One-Layer Transformers are Provably Optimal for In-context Reasoning and Distributional Association Learning in Next-Token Prediction Tasks [11.06955946904705]
  We study the approximation capabilities and on-convergence behaviors of one-layer transformers on the noiseless and noisy in-context reasoning of next-token prediction.<n>Our work addresses gaps by showing that there exists a class of one-layer transformers that are provably Bayes-optimal with both linear and ReLU attention.
  arXiv  Detail & Related papers  (2025-05-21T01:26:44Z)
• Counting Ability of Large Language Models and Impact of Tokenization [17.53620419920189]
  We study the impact of tokenization on the counting abilities of large language models (LLMs) Our work investigates the impact of tokenization on the counting abilities of LLMs, uncovering substantial performance variations based on input tokenization differences.
  arXiv  Detail & Related papers  (2024-10-25T17:56:24Z)
• Interpreting Affine Recurrence Learning in GPT-style Transformers [54.01174470722201]
  In-context learning allows GPT-style transformers to generalize during inference without modifying their weights. This paper focuses specifically on their ability to learn and predict affine recurrences as an ICL task. We analyze the model's internal operations using both empirical and theoretical approaches.
  arXiv  Detail & Related papers  (2024-10-22T21:30:01Z)
• Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning? [69.4145579827826]
  We show a fast flow on the regression loss despite the gradient non-ity algorithms for our convergence landscape. This is the first theoretical analysis for multi-layer Transformer in this setting.
  arXiv  Detail & Related papers  (2024-10-10T18:29:05Z)
• Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis [82.51626700527835]
  Chain-of-shift (CoT) is an efficient method that enables the reasoning ability of large language models by augmenting the query using examples with multiple intermediate steps.<n>We show that despite the theoretical success of CoT, it fails to provide an accurate generalization when CoT does.
  arXiv  Detail & Related papers  (2024-10-03T03:12:51Z)
• A Theoretical Understanding of Self-Correction through In-context Alignment [51.622068973630796]
  Large language models (LLMs) are capable of improving their abilities purely by self-correction. We show that when LLMs give relatively accurate self-examinations as rewards, they are capable of refining responses in an in-context way. Inspired by these findings, we also illustrate applications of self-correction, such as defending against LLM jailbreaks.
  arXiv  Detail & Related papers  (2024-05-28T22:33:02Z)
• On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability [34.43255978863601]
  Several suggest that transformers learn a mesa-optimizer during autorere training. We show that a stronger assumption related to the moments of data is the sufficient necessary condition that the learned mesa-optimizer can perform.
  arXiv  Detail & Related papers  (2024-05-27T05:41:06Z)
• Trained Transformers Learn Linear Models In-Context [39.56636898650966]
  Attention-based neural networks as transformers have demonstrated a remarkable ability to exhibit inattention learning (ICL) We show that when transformer training over random instances of linear regression problems, these models' predictions mimic nonlinear of ordinary squares.
  arXiv  Detail & Related papers  (2023-06-16T15:50:03Z)
• Understanding the Difficulty of Training Transformers [120.99980924577787]
  We show that unbalanced gradients are not the root cause of the instability of training. We propose Admin to stabilize the early stage's training and unleash its full potential in the late stage.
  arXiv  Detail & Related papers  (2020-04-17T13:59:07Z)

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.