Zobrazeno 1 - 10
of 65
pro vyhledávání: '"Zhang, Kexun"'
Autor:
Xie, Jian, Zhang, Kexun, Chen, Jiangjie, Yuan, Siyu, Zhang, Kai, Zhang, Yikai, Li, Lei, Xiao, Yanghua
Autonomous planning has been an ongoing pursuit since the inception of artificial intelligence. Based on curated problem solvers, early planning agents could deliver precise solutions for specific tasks but lacked generalization. The emergence of lar
Externí odkaz:
http://arxiv.org/abs/2410.12409
As AI advances in text generation, human trust in AI generated content remains constrained by biases that go beyond concerns of accuracy. This study explores how bias shapes the perception of AI versus human generated content. Through three experimen
Externí odkaz:
http://arxiv.org/abs/2410.03723
Autor:
Zhang, Kexun, Yao, Weiran, Liu, Zuxin, Feng, Yihao, Liu, Zhiwei, Murthy, Rithesh, Lan, Tian, Li, Lei, Lou, Renze, Xu, Jiacheng, Pang, Bo, Zhou, Yingbo, Heinecke, Shelby, Savarese, Silvio, Wang, Huan, Xiong, Caiming
Large language model (LLM) agents have shown great potential in solving real-world software engineering (SWE) problems. The most advanced open-source SWE agent can resolve over 27% of real GitHub issues in SWE-Bench Lite. However, these sophisticated
Externí odkaz:
http://arxiv.org/abs/2408.07060
Autor:
Wang, Xinyi, Antoniades, Antonis, Elazar, Yanai, Amayuelas, Alfonso, Albalak, Alon, Zhang, Kexun, Wang, William Yang
The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing vast amounts of pretraining data. To explore this issue, we introduce a
Externí odkaz:
http://arxiv.org/abs/2407.14985
Autor:
Naik, Atharva, Zhang, Kexun, Robinson, Nathaniel, Mysore, Aravind, Marr, Clayton, Byrnes, Hong Sng Rebecca, Cai, Anna, Chang, Kalvin, Mortensen, David
Historical linguists have long written a kind of incompletely formalized ''program'' that converts reconstructed words in an ancestor language into words in one of its attested descendants that consist of a series of ordered string rewrite functions
Externí odkaz:
http://arxiv.org/abs/2406.12725
Large language models (LLMs) are increasingly employed for complex tasks that process multiple generation calls in a tree structure with shared prefixes of tokens, including few-shot prompting, multi-step reasoning, speculative decoding, etc. However
Externí odkaz:
http://arxiv.org/abs/2404.00242
How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform well in unseen, endangered languages. On the contrary, we observe that 2
Externí odkaz:
http://arxiv.org/abs/2402.18025
Autor:
Wang, Xinyi, Amayuelas, Alfonso, Zhang, Kexun, Pan, Liangming, Chen, Wenhu, Wang, William Yang
Pre-trained language models (LMs) are able to perform complex reasoning without explicit fine-tuning. To understand how pre-training with a next-token prediction objective contributes to the emergence of such reasoning capability, we propose that we
Externí odkaz:
http://arxiv.org/abs/2402.03268
Instruction-tuned large language models (LLMs) excel at many tasks but often fail to use external tools due to complicated and unfamiliar syntax constraints. While extensive fine-tuning and prompting can mitigate the issue, these approaches are expen
Externí odkaz:
http://arxiv.org/abs/2310.07075
This work proposes a training-free approach for the detection of LLMs-generated codes, mitigating the risks associated with their indiscriminate usage. To the best of our knowledge, our research is the first to investigate zero-shot detection techniq
Externí odkaz:
http://arxiv.org/abs/2310.05103