Large-Scale Constraint Generation - Can LLMs Parse Hundreds of Constraints?

• URL: http://arxiv.org/abs/2509.24090v1
• Date: Sun, 28 Sep 2025 21:55:53 GMT
• Title: Large-Scale Constraint Generation - Can LLMs Parse Hundreds of Constraints?
• Abstract summary: Large-Scale Constraint Generation (LSCG) is a new problem that evaluates whether Large Language Models can parse a large, fine-grained, generic list of constraints.<n>In Words Checker, we evaluate the impact of model characteristics (e.g., size, family) and steering techniques (e.g., Simple Prompt, Chain of Thought, Best of N) on performance.<n>We propose FoCusNet, a small and dedicated model that parses the original list of constraints into a smaller subset, helping the LLM focus on relevant constraints.
• Score: 20.47853693801739
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent research has explored the constrained generation capabilities of Large Language Models (LLMs) when explicitly prompted by few task-specific requirements. In contrast, we introduce Large-Scale Constraint Generation (LSCG), a new problem that evaluates whether LLMs can parse a large, fine-grained, generic list of constraints. To examine the LLMs' ability to handle an increasing number constraints, we create a practical instance of LSCG, called Words Checker. In Words Checker, we evaluate the impact of model characteristics (e.g., size, family) and steering techniques (e.g., Simple Prompt, Chain of Thought, Best of N) on performance. We also propose FoCusNet, a small and dedicated model that parses the original list of constraints into a smaller subset, helping the LLM focus on relevant constraints. Experiments reveal that existing solutions suffer a significant performance drop as the number of constraints increases, with FoCusNet showing an 8-13% accuracy boost.

Related papers

• Programming over Thinking: Efficient and Robust Multi-Constraint Planning [54.77940831026738]
  SCOPE is a framework that disentangles query-specific reasoning from generic code execution.<n>SCOPE achieves state-of-the-art performance while lowering cost and latency.
  arXiv  Detail & Related papers  (2026-01-14T02:58:07Z)
• "Don't Do That!": Guiding Embodied Systems through Large Language Model-based Constraint Generation [40.61171036032532]
  Large language models (LLMs) have spurred interest in robotic navigation that incorporates complex constraints from natural language into the planning problem.<n>In this paper, we propose a constraint generation framework that uses LLMs to translate constraints into Python functions.<n>We show that these LLM-generated functions accurately describe even complex mathematical constraints, and apply them to point cloud representations with traditional search algorithms.
  arXiv  Detail & Related papers  (2025-06-04T22:47:53Z)
• Large Language Model Meets Constraint Propagation [42.54350568915404]
  GenCP combines predictions with Constraint Programming (CP) reasoning to generate fluent text.<n>We improve GenCP by integrating Masked Language Models (MLMs) for domain generation, which allows constraint propagation.<n>Our evaluation on COLLIE benchmarks demonstrates that incorporating domain preview via bidirectional calls significantly improves GenCP's performance.
  arXiv  Detail & Related papers  (2025-05-29T21:18:12Z)
• Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models [39.114513139453756]
  It is crucial for large language models (LLMs) to follow instructions that involve multiple constraints.<n>We design a pipeline to construct datasets with high-quality outputs automatically.<n>To fully utilize the positive and negative samples generated during the data construction process, we choose Direct Preference Optimization (DPO) as the training method.<n>We experimentally evaluate the effectiveness of our methods in improving LLMs' soft constraint following ability.
  arXiv  Detail & Related papers  (2025-01-09T03:34:07Z)
• Control Large Language Models via Divide and Conquer [94.48784966256463]
  This paper investigates controllable generation for large language models (LLMs) with prompt-based control, focusing on Lexically Constrained Generation (LCG) We evaluate the performance of LLMs on satisfying lexical constraints with prompt-based control, as well as their efficacy in downstream applications.
  arXiv  Detail & Related papers  (2024-10-06T21:20:06Z)
• Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models [59.970391602080205]
  This study investigates whether such constraints on generation space impact LLMs abilities, including reasoning and domain knowledge comprehension. We evaluate LLMs performance when restricted to adhere to structured formats versus generating free-form responses across various common tasks. We find that stricter format constraints generally lead to greater performance degradation in reasoning tasks.
  arXiv  Detail & Related papers  (2024-08-05T13:08:24Z)
• FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models [79.62191017182518]
  FollowBench is a benchmark for Fine-grained Constraints Following Benchmark for Large Language Models. We introduce a Multi-level mechanism that incrementally adds a single constraint to the initial instruction at each increased level. By evaluating 13 popular LLMs on FollowBench, we highlight the weaknesses of LLMs in instruction following and point towards potential avenues for future work.
  arXiv  Detail & Related papers  (2023-10-31T12:32:38Z)
• Evaluating, Understanding, and Improving Constrained Text Generation for Large Language Models [49.74036826946397]
  This study investigates constrained text generation for large language models (LLMs) Our research mainly focuses on mainstream open-source LLMs, categorizing constraints into lexical, structural, and relation-based types. Results illuminate LLMs' capacity and deficiency to incorporate constraints and provide insights for future developments in constrained text generation.
  arXiv  Detail & Related papers  (2023-10-25T03:58:49Z)
• QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models [85.02796681773447]
  We propose a quantization-aware low-rank adaptation (QA-LoRA) algorithm. The motivation lies in the imbalanced degrees of freedom of quantization and adaptation. QA-LoRA is easily implemented with a few lines of code.
  arXiv  Detail & Related papers  (2023-09-26T07:22:23Z)
• LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
  Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset. Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
  arXiv  Detail & Related papers  (2023-05-19T12:10:53Z)
• On Codex Prompt Engineering for OCL Generation: An Empirical Study [10.184056098238765]
  The Object Constraint Language (OCL) is a declarative language that adds constraints and object query expressions to MOF models. Recent advancements in LLMs, such as GPT-3, have shown their capability in many NLP tasks. We investigate the reliability of OCL constraints generated by Codex from natural language specifications.
  arXiv  Detail & Related papers  (2023-03-28T18:50:51Z)

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.