UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following

• URL: http://arxiv.org/abs/2608.09154v1
• Date: Mon, 10 Aug 2026 06:01:31 GMT
• Title: UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following
• Abstract summary: UNSPECIFIC is a framework that synthesizes constraints common to two similar reference articles to reduce copy-pasting.<n>We build the UNSPECIFIC benchmark on news, story, and blog domains to analyze the copy-pasting behavior of LLMs.
• Score: 25.631351524871636
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly expected to follow long lists of constraints in complex instructions, and synthesizing instructions from a reference document (i.e., back-translation) is a widely used method to measure/enhance LLMs' ability to follow complex instructions. However, this method introduces a critical loophole: the constraint synthesis model copies text from the reference as a very specific constraint and the evaluated LLM trivially satisfies the constraint by copying its text in the response. To address these issues, we propose UNSPECIFIC, a novel framework that synthesizes constraints common to two similar reference articles to reduce copy-pasting, selectively hardens only trivially satisfied constraints to balance difficulty and naturalness, and evaluates satisfaction on both the generated article and its summary to penalize superficial instruction following. Consequently, we built the UNSPECIFIC benchmark on news, story, and blog domains to analyze the copy-pasting behavior of LLMs. Our results show that our synthesized constraints are not only more challenging (e.g., the satisfaction rate of GPT-5 Mini drops from 90% to 78%) and natural (LLM win-rate gap improves by 30%) from a human perspective but also mitigate the copy-pasting. We also find that a large portion of constraints are satisfied superficially (i.e., not satisfied in the core narrative of the article). The code and datasets are released at https://github.com/JeetDSharma/UNSPECIFIC.

Related papers

• From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks [49.57538588967748]
  Large language models (LLMs) exhibit failures on elementary symbolic tasks such as character counting in a word, despite excelling on complex benchmarks.<n>We uncover a consistent phenomenon across modern architectures, including LLaMA, Qwen, and Gemma.<n>We show that symbolic reasoning failures in LLMs are not due to missing representations or insufficient scale, but arise from structured interference within the model's computation graph.
  arXiv  Detail & Related papers  (2026-04-01T11:40:12Z)
• RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis [78.32151470154422]
  We introduce RAVEL, an agentic framework that enables the testers to autonomously plan and execute typical synthesis operations.<n>We present C3EBench, a benchmark comprising 1,258 samples derived from professional human writings.<n>By augmenting RAVEL with SOTA LLMs as operators, we find that such agentic text synthesis is dominated by the LLM's reasoning capability.
  arXiv  Detail & Related papers  (2026-02-28T14:47:34Z)
• Chain of Summaries: Summarization Through Iterative Questioning [0.0]
  Large Language Models (LLMs) are increasingly using external web content.<n>Much of this content is not easily digestible by LLMs due to LLM-unfriendly formats and limitations of context length.<n>We propose a method for generating general-purpose, information-dense summaries that act as plain-text repositories of web content.
  arXiv  Detail & Related papers  (2025-11-12T16:53:37Z)
• Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following [39.114513139453756]
  Real-world instructions with multiple constraints pose a significant challenge to existing large language models (LLMs)<n>We quantitatively measure the difficulty distribution of the constraints by a novel Difficulty Distribution Index (CDDI)<n>We find that LLMs are more performant when presented with the constraints in a hard-to-easy'' order.
  arXiv  Detail & Related papers  (2025-02-24T14:39:28Z)
• Constraint Back-translation Improves Complex Instruction Following of Large Language Models [55.60192044049083]
  Large language models (LLMs) struggle to follow instructions with complex constraints in format, length, etc.<n>Previous works conduct post-training on complex instruction-response pairs generated by feeding complex instructions to advanced LLMs.<n>We propose a novel data generation technique, constraint back-translation.
  arXiv  Detail & Related papers  (2024-10-31T17:42:26Z)
• Divide-Verify-Refine: Can LLMs Self-Align with Complex Instructions? [33.18076221854853]
  We propose a framework to divide complex instructions into single constraints and prepare appropriate tools.<n>We then verify responses using tools that provide rigorous check and textual guidance.<n>To maximize refinement effectiveness, we propose dynamic few-shot prompting, where a refinement repository collects successful refinements.
  arXiv  Detail & Related papers  (2024-10-16T04:01:55Z)
• LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints [86.59857711385833]
  We introduce RealInstruct, the first benchmark designed to evaluate LLMs' ability to follow real-world multi-constrained instructions. To address the performance gap between open-source and proprietary models, we propose the Decompose, Critique and Refine (DeCRIM) self-correction pipeline. Our results show that DeCRIM improves Mistral's performance by 7.3% on RealInstruct and 8.0% on IFEval even with weak feedback.
  arXiv  Detail & Related papers  (2024-10-09T01:25:10Z)
• Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models [79.70436109672599]
  We derive non-vacuous generalization bounds for large language models as large as LLaMA2-70B. Our work achieves the first non-vacuous bounds for models that are deployed in practice and generate high-quality text.
  arXiv  Detail & Related papers  (2024-07-25T16:13:58Z)
• Chain-of-Specificity: An Iteratively Refining Method for Eliciting Knowledge from Large Language Models [27.615355663475984]
  Large Language Models (LLMs) exhibit remarkable generative capabilities, enabling the generation of valuable information. Existing approaches attempted to address this issue by decomposing or rewriting input instructions. This paper proposes a simple yet effective method named Chain-of-Specificity (CoS)
  arXiv  Detail & Related papers  (2024-02-20T08:03:05Z)
• 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)

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.