Teaching by Failure: Counter-Example-Driven Curricula for Transformer Self-Improvement

• URL: http://arxiv.org/abs/2512.01187v1
• Date: Mon, 01 Dec 2025 02:00:41 GMT
• Title: Teaching by Failure: Counter-Example-Driven Curricula for Transformer Self-Improvement
• Authors: Harshil Vejendla,
• Abstract summary: Transformer models often exhibit brittle extrapolation, failing on inputs that are longer or structurally more complex than those seen during training.<n>We introduce Counter-Example-Driven Curricula (CEDC), an automated framework that improves model robustness by iteratively focusing on its own failures.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer models often exhibit brittle extrapolation, failing on inputs that are longer or structurally more complex than those seen during training. We introduce Counter-Example-Driven Curricula (CEDC), an automated framework that improves model robustness by iteratively focusing on its own failures. At each step, CEDC uses the current model to generate a diverse set of candidate problems, employs a fast, executable verifier to identify incorrect predictions (counter-examples), and then fine-tunes the model on a dataset enriched with these discovered failures. We evaluate CEDC on a suite of algorithmic and natural language tasks, including integer addition, sorting, Dyck-2 language recognition, and three text classification benchmarks. Compared to static training and standard curriculum learning baselines, CEDC achieves up to 30x greater length extrapolation, is 3.75x more computationally efficient than uniform data augmentation, and requires no manual difficulty heuristics. We provide a detailed analysis of the counter-examples, showing how the curriculum naturally adapts to target progressively more complex error modes. Our findings establish verifier-guided, failure-driven learning as a simple, powerful, and efficient paradigm for enhancing the generalization capabilities of Transformer models.

Related papers

• Automatic Syntax Error Repair for Discrete Controller Synthesis using Large Language Model [8.741815980649667]
  This paper presents an automated approach that leverages Large Language Models (LLMs) to repair syntax errors in DCS models.<n>It equips the LLM with DCS-specific domain knowledge, including formal grammar rules and illustrative examples, to guide accurate corrections.<n>It achieves a speedup of 3.46 times compared to human developers.
  arXiv  Detail & Related papers  (2025-12-08T07:57:15Z)
• Detect Anything via Next Point Prediction [51.55967987350882]
  Rex- Omni is a 3B-scale MLLM that achieves state-of-the-art object perception performance.<n>On benchmarks like COCO and LVIS, Rex- Omni attains performance comparable to or exceeding regression-based models.
  arXiv  Detail & Related papers  (2025-10-14T17:59:54Z)
• Continuous Self-Improvement of Large Language Models by Test-time Training with Verifier-Driven Sample Selection [6.471199527741301]
  We introduce a new framework called VDS-TTT - Verifier-Driven Sample Selection for Test-Time Training.<n>We use a learned verifier to score a pool of generated responses and select only from high ranking pseudo-labeled examples for fine-tuned adaptation.<n>We fine-tune only low-rank LoRA adapter parameters, ensuring adaptation efficiency and fast convergence.
  arXiv  Detail & Related papers  (2025-05-26T03:54:47Z)
• Consistency-based Abductive Reasoning over Perceptual Errors of Multiple Pre-trained Models in Novel Environments [5.5855749614100825]
  This paper addresses the hypothesis that leveraging multiple pre-trained models can mitigate this recall reduction.<n>We formulate the challenge of identifying and managing conflicting predictions from various models as a consistency-based abduction problem.<n>Our results validate the use of consistency-based abduction as an effective mechanism to robustly integrate knowledge from multiple imperfect models in challenging, novel scenarios.
  arXiv  Detail & Related papers  (2025-05-25T23:17:47Z)
• AdvKT: An Adversarial Multi-Step Training Framework for Knowledge Tracing [64.79967583649407]
  Knowledge Tracing (KT) monitors students' knowledge states and simulates their responses to question sequences.<n>Existing KT models typically follow a single-step training paradigm, which leads to significant error accumulation.<n>We propose a novel Adversarial Multi-Step Training Framework for Knowledge Tracing (AdvKT) which focuses on the multi-step KT task.
  arXiv  Detail & Related papers  (2025-04-07T03:31:57Z)
• In-Context Language Learning: Architectures and Algorithms [73.93205821154605]
  We study ICL through the lens of a new family of model problems we term in context language learning (ICLL) We evaluate a diverse set of neural sequence models on regular ICLL tasks.
  arXiv  Detail & Related papers  (2024-01-23T18:59:21Z)
• Few-shot learning for automated content analysis: Efficient coding of arguments and claims in the debate on arms deliveries to Ukraine [0.9576975587953563]
  Pre-trained language models (PLM) based on transformer neural networks offer great opportunities to improve automatic content analysis in communication science. Three characteristics so far impeded the widespread adoption of the methods in the applying disciplines: the dominance of English language models in NLP research, the necessary computing resources, and the effort required to produce training data to fine-tune PLMs. We test our approach on a realistic use case from communication science to automatically detect claims and arguments together with their stance in the German news debate on arms deliveries to Ukraine.
  arXiv  Detail & Related papers  (2023-12-28T11:39:08Z)
• Generalization Properties of Retrieval-based Models [50.35325326050263]
  Retrieval-based machine learning methods have enjoyed success on a wide range of problems. Despite growing literature showcasing the promise of these models, the theoretical underpinning for such models remains underexplored. We present a formal treatment of retrieval-based models to characterize their generalization ability.
  arXiv  Detail & Related papers  (2022-10-06T00:33:01Z)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)
• HyperImpute: Generalized Iterative Imputation with Automatic Model Selection [77.86861638371926]
  We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models. We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
  arXiv  Detail & Related papers  (2022-06-15T19:10:35Z)
• Discriminative and Generative Transformer-based Models For Situation Entity Classification [8.029049649310211]
  We re-examine the situation entity (SE) classification task with varying amounts of available training data. We exploit a Transformer-based variational autoencoder to encode sentences into a lower dimensional latent space.
  arXiv  Detail & Related papers  (2021-09-15T17:07:07Z)
• Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models [51.744357472072416]
  We propose a method, which continually identifies the weak spots of a model to generate more valuable training instances. Experimental results show that such an adversarial training method combined with the pretraining strategy can improve both the generalization and robustness of multiple CSC models.
  arXiv  Detail & Related papers  (2021-05-31T09:17:33Z)

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.