相关论文: WorkflowPerturb: Calibrated Stress Tests for Evalu…

The growing need for synthetic time series, due to data augmentation or privacy regulations, has led to numerous generative models, frameworks, and evaluation measures alike. Objectively comparing these measures on a large scale remains an…

Large language models (LLMs) have demonstrated strong capabilities across various language tasks, notably through instruction-tuning methods. However, LLMs face challenges in visualizing complex, real-world data through charts and plots.…

Large Language Models (LLMs) become the start-of-the-art solutions for a variety of natural language tasks and are integrated into real-world applications. However, LLMs can be potentially harmful in manifesting undesirable safety issues…

We present GenderBench -- a comprehensive evaluation suite designed to measure gender biases in LLMs. GenderBench includes 14 probes that quantify 19 gender-related harmful behaviors exhibited by LLMs. We release GenderBench as an…

Large language models (LLMs) are typically aligned to a universal set of safety and usage principles intended for broad public acceptability. Yet, real-world applications of LLMs often take place within organizational ecosystems shaped by…

As generative AI systems are increasingly deployed in real-world applications, regulating multiple dimensions of model behavior has become essential. We focus on test-time filtering: a lightweight mechanism for behavior control that…

Human beings often experience stress, which can significantly influence their performance. This study explores whether Large Language Models (LLMs) exhibit stress responses similar to those of humans and whether their performance fluctuates…

Large language models (LLMs) are increasingly deployed in multilingual, real-world applications with user inputs -- naturally introducing \emph{typographical errors} (typos). Yet most benchmarks assume clean input, leaving the robustness of…

Modern translation workflows demand more than semantic equivalence. Users routinely require models to preserve JSON or HTML schemas, honor curated glossaries, disambiguate with provided context, and match prescribed registers, often several…

Robust workflow composition is critical for effective agent performance, yet progress in Large Language Model (LLM) planning and reasoning is hindered by a scarcity of scalable evaluation data. This work introduces NL2Flow, a fully…

Despite advances in large language models (LLMs) on reasoning and instruction-following tasks, it is unclear whether they can reliably produce outputs aligned with a variety of user goals, a concept called steerability. Two gaps in current…

Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive. Despite…

Large Language Models (LLMs) have seen great advance in both academia and industry, and their popularity results in numerous open-source frameworks and techniques in accelerating LLM pre-training, fine-tuning, and inference. Training and…

Context: Dynamic production environments make it challenging to maintain reliable machine learning (ML) systems. Runtime issues, such as changes in data patterns or operating contexts, that degrade model performance are a common occurrence…

The aim of this study is to determine the perceived stress levels of 150 individuals and analyze the responses given to adapted questions in Turkish using machine learning. The test consists of 14 questions, each scored on a scale of 0 to…

The development of LLM agents has led to a growing body of work on knowledge-work AI, including coding, research, and healthcare. However, current knowledge-work evaluation and benchmark design still largely follow the logic of traditional…

We introduce $\textbf{SimuHome}$, a high-fidelity smart home simulator and a benchmark of 600 episodes for LLM-based smart home agents. Existing smart home benchmarks treat the home as a static system, neither simulating how device…

Overlapping calendar invitations force busy professionals to repeatedly decide which meetings to attend, reschedule, or decline. We refer to this preference-driven decision process as calendar conflict resolution. Automating this decision…

The monitoring of machine conditions in a plant is crucial for production in manufacturing. A sudden failure of a machine can stop production and cause a loss of revenue. The vibration signal of a machine is a good indicator of its…

Large Language Models (LLMs) have demonstrated remarkable capabilities in software engineering, yet comprehensive benchmarks covering diverse SE activities remain limited. We present a multi-task evaluation of 11 state-of-the-art LLMs…