Even though large language models (LLMs) have demonstrated remarkable
capability in solving various natural language tasks, the capability of an LLM
to follow human instructions is still a concern. Recent works have shown great
improvements in the instruction-following capability via additional training
for instruction-following tasks. However, the mechanisms responsible for
effective instruction-following capabilities remain inadequately understood.
Here, we introduce a simplified instruction-following task and use synthetic
datasets to analyze a Transformer-based causal language model. Our findings
suggest that the model learns task-specific information by clustering data
within its hidden space, with this clustering process evolving dynamically
during learning. We also demonstrate how this phenomenon assists the model in
handling unseen instances and validate our results in a more realistic setting.

通过对合成数据集的分析，我们发现大规模语言模型通过将数据在其隐藏空间内进行聚类学习特定任务的信息，并且这个聚类过程在学习过程中动态演化，从而帮助模型处理未知的实例。

基于 Transformer 的因果语言模型进行聚类

Transformer-based Causal Language Models Perform Clustering

The ability to follow instructions is crucial to Large Language Models (LLMs)
to handle various real-world applications. Existing benchmarks primarily focus
on evaluating superficial response quality, which does not necessarily indicate
instruction-following capability. To fill this research gap, in this paper, we
propose FollowBench, a Multi-level Fine-grained Constraints Following Benchmark
for LLMs. FollowBench comprehensively includes five different types (i.e.,
Content, Scenario, Style, Format, and Example) of fine-grained constraints. To
enable a precise constraint following estimation, we introduce a Multi-level
mechanism that incrementally adds a single constraint to the initial
instruction at each level. To evaluate whether LLMs' outputs have satisfied
every individual constraint, we propose to prompt strong LLMs with constraint
evolution paths to handle challenging semantic constraints. By evaluating nine
closed-source and open-source popular LLMs on FollowBench, we highlight the
weaknesses of LLMs in instruction following and point towards potential avenues
for future work. The data and code are publicly available at
this https URL

本文提出了 FollowBench，这是一个用于大型语言模型（LLMs）的多级细粒度约束遵循基准，通过评估 LLMs 在遵循不同类型的细粒度约束方面的表现，揭示了 LLMs 在遵循指令方面的不足之处，并指出了未来研究的潜在方向。