Zobrazeno 1 - 10
of 662
pro vyhledávání: '"Lin, HongYu"'
Autor:
Lu, Xinyu, Wen, Xueru, Lu, Yaojie, Yu, Bowen, Lin, Hongyu, Yu, Haiyang, Sun, Le, Han, Xianpei, Li, Yongbin
As post-training processes utilize increasingly large datasets and base models continue to grow in size, the computational demands and implementation challenges of existing algorithms are escalating significantly. In this paper, we propose modeling t
Externí odkaz:
http://arxiv.org/abs/2410.21027
Autor:
Xiang, Hao, Yu, Bowen, Lin, Hongyu, Lu, Keming, Lu, Yaojie, Han, Xianpei, Sun, Le, Zhou, Jingren, Lin, Junyang
Automated alignment develops alignment systems with minimal human intervention. The key to automated alignment lies in providing learnable and accurate preference signals for preference learning without human annotation. In this paper, we introduce S
Externí odkaz:
http://arxiv.org/abs/2410.17131
Post-training has emerged as a crucial paradigm for adapting large-scale pre-trained models to various tasks, whose effects are fully reflected by delta parameters (i.e., the disparity between post-trained and pre-trained parameters). While numerous
Externí odkaz:
http://arxiv.org/abs/2410.13841
Autor:
Li, Zhuoqun, Chen, Xuanang, Yu, Haiyang, Lin, Hongyu, Lu, Yaojie, Tang, Qiaoyu, Huang, Fei, Han, Xianpei, Sun, Le, Li, Yongbin
Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful information require
Externí odkaz:
http://arxiv.org/abs/2410.08815
Evaluating the quality of documents is essential for filtering valuable content from the current massive amount of information. Conventional approaches typically rely on a single score as a supervision signal for training content quality evaluators,
Externí odkaz:
http://arxiv.org/abs/2410.07693
Autor:
Li, Zichao, He, Shaojie, Liao, Meng, Chen, Xuanang, Lu, Yaojie, Lin, Hongyu, Lu, Yanxiong, Han, Xianpei, Sun, Le
Document logical structuring aims to extract the underlying hierarchical structure of documents, which is crucial for document intelligence. Traditional approaches often fall short in handling the complexity and the variability of lengthy documents.
Externí odkaz:
http://arxiv.org/abs/2410.06802
Autor:
Wen, Xueru, Lou, Jie, Lu, Yaojie, Lin, Hongyu, Yu, Xing, Lu, Xinyu, He, Ben, Han, Xianpei, Zhang, Debing, Sun, Le
Reward Models (RMs) are crucial for aligning language models with human preferences. Currently, the evaluation of RMs depends on measuring accuracy against a validation set of manually annotated preference data. Although this method is straightforwar
Externí odkaz:
http://arxiv.org/abs/2410.05584
Autor:
Li, Zichao, Abulaiti, Aizier, Lu, Yaojie, Chen, Xuanang, Zheng, Jia, Lin, Hongyu, Han, Xianpei, Sun, Le
Document Structured Extraction (DSE) aims to extract structured content from raw documents. Despite the emergence of numerous DSE systems, their unified evaluation remains inadequate, significantly hindering the field's advancement. This problem is l
Externí odkaz:
http://arxiv.org/abs/2409.05137
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 a crucial mechanism for enhancing the reasoning performance of LLMs. However, current approaches mainly involve basic prompts for intuitive instance-level feedback, which resembles System-1 processes and limits the reasoning ca
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