7 papers
Harnesses for Inference-Time Alignment over Execution Trajectories
Boyuan Wang, Bochao Li, Minghan Wang +2
Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition a…
GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler
Minghan Wang, Ye Bai, Thuy-Trang Vu +2
Inference-time scaling (ITS) in latent reasoning models typically relies on heuristic perturbations, such as dropout or fixed Gaussian noise, to generate diverse candidate trajecto…
NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions
Haolin Yang, Yuxing Long, Zhuoyuan Yu +8
Instruction-following navigation is a key step toward embodied intelligence. Prior benchmarks mainly focus on semantic understanding but overlook systematically evaluating navigati…
OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs
Hasan Iqbal, Yuxia Wang, Minghan Wang +4
The increased use of large language models (LLMs) across a variety of real-world applications calls for automatic tools to check the factual accuracy of their outputs, as LLMs ofte…
OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs
Yuxia Wang, Minghan Wang, Hasan Iqbal +3
The increased use of large language models (LLMs) across a variety of real-world applications calls for mechanisms to verify the factual accuracy of their outputs. Difficulties lie…
Qorgau: Evaluating LLM Safety in Kazakh-Russian Bilingual Contexts
Maiya Goloburda, Nurkhan Laiyk, Diana Turmakhan +11
Large language models (LLMs) are known to have the potential to generate harmful content, posing risks to users. While significant progress has been made in developing taxonomies f…