Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability

• URL: http://arxiv.org/abs/2506.15629v1
• Date: Wed, 18 Jun 2025 17:00:54 GMT
• Title: Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability
• Authors: Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe,
• Abstract summary: In generative commonsense reasoning tasks, generative large language models (LLMs) compose sentences that include all given concepts.<n>This benchmark measures ordered coverage to assess whether concepts are generated in the specified order.<n>Even the most instruction-compliant LLM achieved only about 75% ordered coverage, highlighting the need for improvements in both instruction-following and compositional generalization capabilities.
• Score: 27.84922167294656
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In generative commonsense reasoning tasks such as CommonGen, generative large language models (LLMs) compose sentences that include all given concepts. However, when focusing on instruction-following capabilities, if a prompt specifies a concept order, LLMs must generate sentences that adhere to the specified order. To address this, we propose Ordered CommonGen, a benchmark designed to evaluate the compositional generalization and instruction-following abilities of LLMs. This benchmark measures ordered coverage to assess whether concepts are generated in the specified order, enabling a simultaneous evaluation of both abilities. We conducted a comprehensive analysis using 36 LLMs and found that, while LLMs generally understand the intent of instructions, biases toward specific concept order patterns often lead to low-diversity outputs or identical results even when the concept order is altered. Moreover, even the most instruction-compliant LLM achieved only about 75% ordered coverage, highlighting the need for improvements in both instruction-following and compositional generalization capabilities.

Related papers

• RELIC: Evaluating Compositional Instruction Following via Language Recognition [37.49115450182637]
  Large language models (LLMs) are increasingly expected to perform tasks based only on a specification of the task provided in context.<n>We introduce the Recognition of Languages In-Context (RELIC) framework to evaluate instruction following using language recognition.
  arXiv  Detail & Related papers  (2025-06-05T16:17:24Z)
• Ask, Fail, Repeat: Meeseeks, an Iterative Feedback Benchmark for LLMs' Multi-turn Instruction-Following Ability [5.393872292662451]
  Meeseeks simulates realistic human-LLM interactions through an iterative feedback framework.<n>Meeseeks provides valuable insights into LLMs' instruction-following capabilities in multi-turn scenarios.
  arXiv  Detail & Related papers  (2025-04-30T13:28:19Z)
• Benchmarking Complex Instruction-Following with Multiple Constraints Composition [72.82640456309821]
  How to evaluate the ability of complex instruction-following of large language models (LLMs) has become a critical research problem. Existing benchmarks mainly focus on modeling different types of constraints in human instructions while neglecting the composition of different constraints. We propose ComplexBench, a benchmark for comprehensively evaluating the ability of LLMs to follow complex instructions composed of multiple constraints.
  arXiv  Detail & Related papers  (2024-07-04T14:50:45Z)
• DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation [57.07295906718989]
  Constrained decoding approaches aim to control the meaning or style of text generated by pre-trained large language (Ms also PLMs) for various tasks at inference time.<n>These methods often guide plausible continuations by greedily and explicitly selecting targets.<n>Inspired by cognitive dual-process theory, we propose a novel decoding framework DECIDER.
  arXiv  Detail & Related papers  (2024-03-04T11:49:08Z)
• Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models [54.21695754082441]
  We propose a framework to teach Large Language Models (LLMs) to generate explainable stock predictions. A reflective agent learns how to explain past stock movements through self-reasoning, while the PPO trainer trains the model to generate the most likely explanations. Our framework can outperform both traditional deep-learning and LLM methods in prediction accuracy and Matthews correlation coefficient.
  arXiv  Detail & Related papers  (2024-02-06T03:18:58Z)
• Benchmarking Large Language Models on Controllable Generation under Diversified Instructions [34.89012022437519]
  Large language models (LLMs) have exhibited impressive instruction-following capabilities. It is still unclear whether and to what extent they can respond to explicit constraints that might be entailed in various instructions. We propose a new benchmark CoDI-Eval to evaluate LLMs' responses to instructions with various constraints.
  arXiv  Detail & Related papers  (2024-01-01T07:35:31Z)
• Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization [132.25202059478065]
  We benchmark large language models (LLMs) on instruction controllable text summarization. Our study reveals that instruction controllable text summarization remains a challenging task for LLMs.
  arXiv  Detail & Related papers  (2023-11-15T18:25:26Z)
• 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)
• Learning to Predict Concept Ordering for Common Sense Generation [32.2052248473022]
  We study the relationship between the ordering of the input concepts and the quality of the generated sentences. We find that BART-large model consistently outperforms all other LMs considered in this study. The larger GPT3-based large language models (LLMs) variants do not necessarily outperform much smaller LMs on this task.
  arXiv  Detail & Related papers  (2023-09-12T16:27:18Z)
• Instruction Position Matters in Sequence Generation with Large Language Models [67.87516654892343]
  Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization. We propose enhancing the instruction-following capability of LLMs by shifting the position of task instructions after the input sentences.
  arXiv  Detail & Related papers  (2023-08-23T12:36:57Z)
• Semantic Consistency for Assuring Reliability of Large Language Models [9.040736633675136]
  Large Language Models (LLMs) exhibit remarkable fluency and competence across various natural language tasks.<n>We introduce a general measure of semantic consistency, and formulate multiple versions of this metric to evaluate the performance of various LLMs.<n>We propose a novel prompting strategy, called Ask-to-Choose (A2C), to enhance semantic consistency.
  arXiv  Detail & Related papers  (2023-08-17T18:11:33Z)

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.