Quality follows upgrading
Ever a pioneer, ever a student — learning through our mistakes and failures
Academic
arXiv:2603.12423v1 Announce Type: new Abstract: Negation remains a persistent challenge for modern language models, often causing reversed meanings or factual errors. In this work, we …
arXiv:2603.12453v1 Announce Type: new Abstract: This paper describes our system for SemEval-2026 Task 6, which classifies clarity of responses in political interviews into three categories: …
arXiv:2603.12471v1 Announce Type: new Abstract: Effective personalized feedback is critical to students' literacy development. Though LLM-powered tools now promise to automate such feedback at scale, …
arXiv:2603.12564v1 Announce Type: new Abstract: Tool-augmented LLM agents increasingly serve as multi-turn advisors in high-stakes domains, yet their evaluation relies on ranking-quality metrics that measure …
arXiv:2603.12572v1 Announce Type: new Abstract: Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchmarks, …
arXiv:2603.12577v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) has become a dominant paradigm for deploying LLMs in multi-task scenarios due to its extreme parameter efficiency. …
arXiv:2603.12582v1 Announce Type: new Abstract: Textual adversarial attacks pose a serious security threat to Natural Language Processing (NLP) systems by introducing imperceptible perturbations that mislead …
arXiv:2603.12638v1 Announce Type: new Abstract: The rapid growth of scientific literature has made manual extraction of structured knowledge increasingly impractical. To address this challenge, we …
arXiv:2603.12646v1 Announce Type: new Abstract: System-level routers that intercept LLM requests for safety classification, domain routing, and PII detection must be both fast and operationally …
arXiv:2603.12658v1 Announce Type: new Abstract: Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving …
arXiv:2603.12664v1 Announce Type: new Abstract: Incorporating textual information into time-series forecasting holds promise for addressing event-driven non-stationarity; however, a fundamental modality gap hinders effective fusion: …
arXiv:2603.12677v1 Announce Type: new Abstract: Knowledge editing (KE) aims to precisely rectify specific knowledge in Large Language Models (LLMs) without disrupting general capabilities. State-of-the-art methods …