Xinghua Zhang


2024

pdf bib
Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
Minzheng Wang | Longze Chen | Fu Cheng | Shengyi Liao | Xinghua Zhang | Bingli Wu | Haiyang Yu | Nan Xu | Lei Zhang | Run Luo | Yunshui Li | Min Yang | Fei Huang | Yongbin Li
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Long-context modeling capabilities of Large Language Models (LLMs) have garnered widespread attention, leading to the emergence of LLMs with ultra-context windows. Meanwhile, benchmarks for evaluating long-context language models are gradually catching up. However, existing benchmarks employ irrelevant noise texts to artificially extend the length of test cases, diverging from the real-world scenarios of long-context applications. To bridge this gap, we propose a novel long-context benchmark, Loong, aligning with realistic scenarios through extended multi-document question answering (QA). Unlike typical document QA, in Loong’s test cases, each document is relevant to the final answer, ignoring any document will lead to the failure of the answer. Furthermore, Loong introduces four types of tasks with a range of context lengths: Spotlight Locating, Comparison, Clustering, and Chain of Reasoning, to facilitate a more realistic and comprehensive evaluation of long-context understanding. Extensive experiments indicate that existing long-context language models still exhibit considerable potential for enhancement. Retrieval augmented generation (RAG) achieves poor performance, demonstrating that Loong can reliably assess the model’s long-context modeling capabilities.

pdf bib
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
Zhenhong Zhou | Haiyang Yu | Xinghua Zhang | Rongwu Xu | Fei Huang | Yongbin Li
Findings of the Association for Computational Linguistics: EMNLP 2024

Large language models (LLMs) rely on safety alignment to avoid responding to malicious user inputs. Unfortunately, jailbreak can circumvent safety guardrails, resulting in LLMs generating harmful content and raising concerns about LLM safety. Due to language models with intensive parameters often regarded as black boxes, the mechanisms of alignment and jailbreak are challenging to elucidate. In this paper, we employ weak classifiers to explain LLM safety through the intermediate hidden states. We first confirm that LLMs learn ethical concepts during pre-training rather than alignment and can identify malicious and normal inputs in the early layers. Alignment actually associates the early concepts with emotion guesses in the middle layers and then refines them to the specific reject tokens for safe generations. Jailbreak disturbs the transformation of early unethical classification into negative emotions. We conduct experiments on models from 7B to 70B across various model families to prove our conclusion. Overall, our paper indicates the intrinsical mechanism of LLM safety and how jailbreaks circumvent safety guardrails, offering a new perspective on LLM safety and reducing concerns.

2023

pdf bib
CCL23-Eval 任务1系统报告:基于信息论约束及篇章信息的古籍命名实体识别(System Report for CCL23-Eval Task 1: Information Theory Constraint and Paragraph based Paragraph Classical Named Entity Recognition)
Xinghua Zhang (张兴华) | Tianjun Liu (刘天昀) | Wenyuan Zhang (张文源) | Tingwen Liu (柳厅文)
Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)

“命名实体识别旨在自动识别出文本中具有特定意义的实体(例如,人名、地名),古籍文献中的命名实体识别通过识别人名、书籍、官职等实体,为深度挖掘、组织古汉语人文知识提供重要支撑。现有的中文命名实体识别方法主要聚焦在现代文,但古籍中的实体识别具有更大的挑战,表现在实体的歧义性和边界模糊性两方面。由于古籍行文简练,单字表达加剧了实体的歧义性问题,句读及分词断句难度的提升使实体边界的识别更具挑战性。为有效处理上述问题,本文提出一种基于信息论及篇章信息的古籍命名实体识别方法。通过检索古籍文本的来源信息融入篇章先验知识,并在同一篇章的古籍文本上采取滑动窗口采样增强,以引入篇章背景信息,有效缓解实体歧义性问题。此外,在信息论视角下,约束实体的上下文信息及实体本身特征的编码,最大程度保留泛化特征,去除冗余信息,缓解实体边界模糊的问题,在词义复杂多样、句读困难的古文典籍中提升命名实体识别性能。最终,在token-wise和span-level感知的命名实体识别基础框架下,本文的方法取得了最优的评测性能。”

2021

pdf bib
Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning
Xinghua Zhang | Bowen Yu | Tingwen Liu | Zhenyu Zhang | Jiawei Sheng | Xue Mengge | Hongbo Xu
Findings of the Association for Computational Linguistics: EMNLP 2021

Distantly supervised named entity recognition (DS-NER) efficiently reduces labor costs but meanwhile intrinsically suffers from the label noise due to the strong assumption of distant supervision. Typically, the wrongly labeled instances comprise numbers of incomplete and inaccurate annotations, while most prior denoising works are only concerned with one kind of noise and fail to fully explore useful information in the training set. To address this issue, we propose a robust learning paradigm named Self-Collaborative Denoising Learning (SCDL), which jointly trains two teacher-student networks in a mutually-beneficial manner to iteratively perform noisy label refinery. Each network is designed to exploit reliable labels via self denoising, and two networks communicate with each other to explore unreliable annotations by collaborative denoising. Extensive experimental results on five real-world datasets demonstrate that SCDL is superior to state-of-the-art DS-NER denoising methods.

pdf bib
Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning
Xinghua Zhang | Bowen Yu | Tingwen Liu | Zhenyu Zhang | Jiawei Sheng | Xue Mengge | Hongbo Xu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Distantly supervised named entity recognition (DS-NER) efficiently reduces labor costs but meanwhile intrinsically suffers from the label noise due to the strong assumption of distant supervision. Typically, the wrongly labeled instances comprise numbers of incomplete and inaccurate annotations, while most prior denoising works are only concerned with one kind of noise and fail to fully explore useful information in the training set. To address this issue, we propose a robust learning paradigm named Self-Collaborative Denoising Learning (SCDL), which jointly trains two teacher-student networks in a mutually-beneficial manner to iteratively perform noisy label refinery. Each network is designed to exploit reliable labels via self denoising, and two networks communicate with each other to explore unreliable annotations by collaborative denoising. Extensive experimental results on five real-world datasets demonstrate that SCDL is superior to state-of-the-art DS-NER denoising methods.