Zobrazeno 1 - 10
of 96
pro vyhledávání: '"Lu, Yaojie"'
Autor:
Zheng, Xin, Lou, Jie, Cao, Boxi, Wen, Xueru, Ji, Yuqiu, Lin, Hongyu, Lu, Yaojie, Han, Xianpei, Zhang, Debing, Sun, Le
Self-critic has become an important mechanism for enhancing the reasoning performance of LLMs. However, current approaches mainly involve basic prompts without further training, which tend to be over-simplified, leading to limited accuracy.Moreover,
Externí odkaz:
http://arxiv.org/abs/2408.16326
Code benchmarks such as HumanEval are widely adopted to evaluate the capabilities of Large Language Models (LLMs), providing insights into their strengths and weaknesses. However, current benchmarks primarily exercise LLMs' capability on common codin
Externí odkaz:
http://arxiv.org/abs/2408.13204
Autor:
Xu, Ruiyang, Cao, Jialun, Lu, Yaojie, Lin, Hongyu, Han, Xianpei, He, Ben, Cheung, Shing-Chi, Sun, Le
Code benchmarks such as HumanEval are widely adopted to evaluate Large Language Models' (LLMs) coding capabilities. However, there is an unignorable programming language bias in existing code benchmarks -- over 95% code generation benchmarks are domi
Externí odkaz:
http://arxiv.org/abs/2408.13001
Manually annotating instruction data for large language models is difficult, costly, and hard to scale. Meanwhile, current automatic annotation methods typically rely on distilling synthetic data from proprietary LLMs, which not only limits the upper
Externí odkaz:
http://arxiv.org/abs/2408.10663
Autor:
Zheng, Jiasheng, Cao, Boxi, Ma, Zhengzhao, Pan, Ruotong, Lin, Hongyu, Lu, Yaojie, Han, Xianpei, Sun, Le
In recent years, researchers have proposed numerous benchmarks to evaluate the impressive coding capabilities of large language models (LLMs). However, existing benchmarks primarily focus on assessing the correctness of code generated by LLMs, while
Externí odkaz:
http://arxiv.org/abs/2407.11470
Hallucination occurs when large language models (LLMs) exhibit behavior that deviates from the boundaries of their knowledge during the response generation process. Previous learning-based methods focus on detecting knowledge boundaries and finetunin
Externí odkaz:
http://arxiv.org/abs/2406.12221
The emergence of large language models (LLMs) has increasingly drawn attention to the use of LLMs for human-like planning. Existing work on LLM-based planning either focuses on leveraging the inherent language generation capabilities of LLMs to produ
Externí odkaz:
http://arxiv.org/abs/2406.02903
Autor:
Cao, Boxi, Lu, Keming, Lu, Xinyu, Chen, Jiawei, Ren, Mengjie, Xiang, Hao, Liu, Peilin, Lu, Yaojie, He, Ben, Han, Xianpei, Sun, Le, Lin, Hongyu, Yu, Bowen
Alignment is the most critical step in building large language models (LLMs) that meet human needs. With the rapid development of LLMs gradually surpassing human capabilities, traditional alignment methods based on human-annotation are increasingly u
Externí odkaz:
http://arxiv.org/abs/2406.01252
Autor:
Li, Zhuoqun, Lin, Hongyu, Wang, Tianshu, Cao, Boxi, Lu, Yaojie, Zhou, Weixiang, Wang, Hao, Zeng, Zhenyu, Sun, Le, Han, Xianpei
Linking a claim to grounded references is a critical ability to fulfill human demands for authentic and reliable information. Current studies are limited to specific tasks like information retrieval or semantic matching, where the claim-reference rel
Externí odkaz:
http://arxiv.org/abs/2404.16248
Few-shot NER aims to identify entities of target types with only limited number of illustrative instances. Unfortunately, few-shot NER is severely challenged by the intrinsic precise generalization problem, i.e., it is hard to accurately determine th
Externí odkaz:
http://arxiv.org/abs/2403.16463