The paper introduces a constraint‑aware training objective that externalizes program analysis constraints used during inference, avoiding redundant learning of these constraints during model training. It presents three theorems demonstrating that this approach can reduce model size and improve data efficiency. A controlled synthetic experiment confirms that constraint‑aware training achieves lower prediction loss than standard cross‑entropy training at the same parameter count and data volume.
arXiv:2603. 03305v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to generate executable outputs, JSON objects, and API calls, where a single syntax error can make the output unusable.
RECAST is a new framework that generates datasets with far more constraints per example than existing benchmarks, aiming to push large language models (LLMs) to better follow complex instructions. The authors built RECAST-30K, a 30,000‑instance dataset covering 19 constraint types extracted from real prompt‑response pairs, and showed that fine‑tuning on it improves LLMs’ ability to handle complex tasks without harming general performance. RECAST also provides rule‑based and LLM‑based validators for automatic constraint verification, enabling reward‑based reinforcement learning to further enhance model performance on challenging tasks.
arXiv:2606. 04816v1 Announce Type: new Abstract: Large language models (LLMs) increasingly translate natural-language optimization problems into executable solver code.
arXiv:2508.20443v3 Announce Type: replace Abstract: Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content. Due to growing privacy and ownership...
arXiv:2610.01519v1 Announce Type: cross Abstract: Neuro-Symbolic (NeSy) predictors incorporate prior knowledge into the prediction process of neural networks, ensuring that outputs satisfy specified...
arXiv:2608. 16068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks.
arXiv:2604. 19251v2 Announce Type: replace-cross Abstract: Streamliner constraints reduce the search space of combinatorial problems by ruling out portions of the solution space.
arXiv:2607. 25271v1 Announce Type: cross Abstract: Classical compute-optimal scaling laws assume an unbounded supply of fresh pretraining data, yet pretraining is increasingly entering a regime in which compute grows faster than the availability of high-quality data.
arXiv:2607. 16727v1 Announce Type: new Abstract: Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorrect inference early in a chainof-thought (CoT) trace corrupts all downstream reasoning.
arXiv:2607. 20456v1 Announce Type: cross Abstract: Large language models excel at code generation for mainstream programming languages but struggle with rare, domain-specific languages such as MiniZinc, a constraint modeling language for combinatorial problems.
arXiv:2605. 21751v2 Announce Type: replace Abstract: Text-to-optimization requires two separable capabilities: modeling -- choosing the right optimization structure -- and binding -- grounding every coefficient, index, and parameter in the concrete problem data.
CG4AI is a column generation framework that trains AI models while enforcing linear constraints on their outputs. It constructs a convex combination of models, using a master linear program to set mixture weights and a pricing subproblem to generate new models guided by dual variables, focusing on the most violated constraints. The method is applied to MNIST digit classification—demonstrating constraint learning, adversarial robustness, error correction, and output relabeling—and to multi‑commodity flow routing, achieving feasible predictors with higher accuracy than single‑model baselines.