Recent advancements in Korean large language models (LLMs) have driven numerous benchmarks and evaluation methods, yet inconsistent protocols cause up to 10 p.p performance gaps across institutions. Overcoming these reproducibility gaps does not mean enforcing a one-size-fits-all evaluation. Rather, effective benchmarking requires diverse experimental approaches and a framework robust enough to support them. To this end, we introduce HRET (Haerae Evaluation Toolkit), an open-source, registry-based framework that unifies Korean LLM assessment. HRET integrates major Korean benchmarks, multiple inference backends, and multi-method evaluation, with language consistency enforcement to ensure genuine Korean outputs. Its modular registry design also enables rapid incorporation of new datasets, methods, and backends, ensuring the toolkit adapts to evolving research needs. Beyond standard accuracy metrics, HRET incorporates Korean-focused output analyses-morphology-aware Type-Token Ratio (TTR) for evaluating lexical diversity and systematic keyword-omission detection for identifying missing concepts-to provide diagnostic insights into language-specific behaviors. These targeted analyses help researchers pinpoint morphological and semantic shortcomings in model outputs, guiding focused improvements in Korean LLM development.

Large language models (LLMs) are typically prompted to follow a single instruction per inference call.In this work, we analyze whether LLMs also hold the capability to handle multiple instructions simultaneously, denoted as MULTI-TASK INFERENCE.For this purpose, we introduce the MTI BENCH (Multi-Task Inference Benchmark), a comprehensive evaluation benchmark encompassing 5,000 instances across 25 tasks.Each task in the MTI BENCH involves 2 to 3 sub-tasks.As expected, we first demonstrate that MULTI-TASK INFERENCE reduces the total inference time by ×1.46 times in average since it does not require multiple inference calls.Interestingly, contrary to the expectation that LLMs would perform better when tasks are divided, we find that state-ofthe-art LLMs, such as LLAMA-2-CHAT-70B and GPT-4, show up to 7.3% and 12.4% improved performance with MULTI-TASK INFER-ENCE compared to SINGLE-TASK INFERENCE on the MTI BENCH.We release the MTI BENCH dataset and our code at this link 1 .

Subspace clustering is widely used to find clusters in different subspaces within a dataset. Autoencoders are popular deep subspace clustering methods using feature extraction and dimensional reduction. However, neural networks are vulnerable to overfitting, and therefore have limited potential for unsupervised subspace clustering. This paper proposes a deep multi-view subspace clustering network with feature boosting module to successfully extract meaningful features in different views and to fuse multi-view representations in a complementary manner for enhanced clustering results. The multi-view boosting provides the robust features for unsupervised clustering by emphasizing the features and removing the redundant noise. Quantitative and qualitative analysis on various benchmark datasets verifies that the proposed method outperforms state-of-the-art subspace clustering methods.