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

arXiv: https://arxiv.org/abs/2506.15629 · HTML: https://mlsanity.com/paper/2506.15629/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 67 of its 120 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 67)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [CMMLU: Measuring massive multitask language understanding in Chinese](https://mlsanity.com/paper/2306.09212/) (2023)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [Large Language Models for Data Annotation and Synthesis: A Survey](https://mlsanity.com/paper/2402.13446/) (2024)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions](https://mlsanity.com/paper/2411.14405/) (2024)
- [Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://mlsanity.com/paper/2406.05925/) (2024)
- [ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic](https://mlsanity.com/paper/2402.12840/) (2024)
- [Mixture Models for Diverse Machine Translation: Tricks of the Trade](https://mlsanity.com/paper/1902.07816/) (2019)
- [Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents](https://mlsanity.com/paper/2402.09205/) (2024)
- [Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2211.07634/) (2022)
- [Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU](https://mlsanity.com/paper/2310.04928/) (2023)

## Built on by (most cited first, 10 of 10)

- [Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following](https://mlsanity.com/paper/2512.23457/) (2025)
- [What Drives Compositional Generalization in Visual Generative Models? The Importance of Continuous Training Objectives](https://mlsanity.com/paper/2510.03075/) (2025)
- [GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions](https://mlsanity.com/paper/2609.01491/) (2026)
- [FM SO.P: A Progressive Task Mixture Framework with Automatic Evaluation for Cross-Domain SOP Understanding](https://mlsanity.com/paper/2602.09336/) (2026)
- [Neurosymbolic Language Reasoning as Satisfiability Modulo Theory](https://mlsanity.com/paper/2602.18095/) (2026)
- [AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents](https://mlsanity.com/paper/2604.26522/) (2026)
- [Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning](https://mlsanity.com/paper/2608.05139/) (2026)
- [Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction](https://mlsanity.com/paper/2608.12426/) (2026)
- [The Rise of Verbal Reinforcement Learning](https://mlsanity.com/paper/2609.01597/) (2026)
- [Same Scene, Different Task: Skill Alignment for Compositional Generalization in VLAs](https://mlsanity.com/paper/2610.00524/) (2026)

## Abstract (arXiv)

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.