Cheng Niu


2024

pdf bib
RAG-HAT: A Hallucination-Aware Tuning Pipeline for LLM in Retrieval-Augmented Generation
Juntong Song | Xingguang Wang | Juno Zhu | Yuanhao Wu | Xuxin Cheng | Randy Zhong | Cheng Niu
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track

Retrieval-augmented generation (RAG) has emerged as a significant advancement in the field of large language models (LLMs). By integrating up-to-date information not available during their initial training, RAG greatly enhances the practical utility of LLMs in real-world applications. However, even with RAG, LLMs can still produce inaccurate outputs, such as distorting or misinterpreting source content, posing risks in high-trust scenarios. To address these issues, we introduce a novel approach called Hallucination Aware Tuning (HAT). This method involves training hallucination detection models that generate detection labels and provide detailed descriptions of the detected hallucinations. Utilizing these detection results—particularly the hallucination descriptions—GPT-4 Turbo is employed to correct any detected hallucinations. The corrected outputs, free of hallucinations, along with the original versions, are used to create a preference dataset for Direct Preference Optimization (DPO) training. The fine-tuning through DPO leads to LLMs that exhibit a reduced rate of hallucinations and deliver improved answer quality.

pdf bib
Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation
Cheng Niu | Xingguang Wang | Xuxin Cheng | Juntong Song | Tong Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Dialogue State Tracking (DST) is designed to monitor the evolving dialogue state in the conversations and plays a pivotal role in developing task-oriented dialogue systems. However, obtaining the annotated data for the DST task is usually a costly endeavor. In this paper, we focus on employing LLMs to generate dialogue data to reduce dialogue collection and annotation costs. Specifically, GPT-4 is used to simulate the user and agent interaction, generating thousands of dialogues annotated with DST labels. Then a two-stage fine-tuning on LLaMA 2 is performed on the generated data and the real data for the DST prediction. Experimental results on two public DST benchmarks show that with the generated dialogue data, our model performs better than the baseline trained solely on real data. In addition, our approach is also capable of adapting to the dynamic demands in real-world scenarios, generating dialogues in new domains swiftly. After replacing dialogue segments in any domain with the corresponding generated ones, the model achieves comparable performance to the model trained on real data. The source code and generated dialogue data are available at https://github.com/ParticleMedia/LUAS.

pdf bib
RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models
Cheng Niu | Yuanhao Wu | Juno Zhu | Siliang Xu | KaShun Shum | Randy Zhong | Juntong Song | Tong Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Retrieval-augmented generation (RAG) has become a main technique for alleviating hallucinations in large language models (LLMs). Despite the integration of RAG, LLMs may still present unsupported or contradictory claims to the retrieved contents. In order to develop effective hallucination prevention strategies under RAG, it is important to create benchmark datasets that can measure the extent of hallucination. This paper presents RAGTruth, a corpus tailored for analyzing word-level hallucinations in various domains and tasks within the standard RAG frameworks for LLM applications. RAGTruth comprises nearly 18,000 naturally generated responses from diverse LLMs using RAG. These responses have undergone meticulous manual annotations at both the individual case and word levels, incorporating evaluations of hallucination intensity. We not only benchmark hallucination frequencies across different LLMs, but also critically assess the effectiveness of several existing hallucination detection methodologies. We show that using a high-quality dataset such as RAGTruth, it is possible to finetune a relatively small LLM and achieve a competitive hallucination detection performance when compared to the existing prompt-based approaches using state-of-the-art LLMs such as GPT-4. Furthermore, the finetuned model can effectively mitigate hallucination in LLM responses.

pdf bib
VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning
Cheng Niu | Yang Guan | Yuanhao Wu | Juno Zhu | Juntong Song | Randy Zhong | Kaihua Zhu | Siliang Xu | Shizhe Diao | Tong Zhang
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)

The proliferation of fake news poses a significant threat not only by disseminating misleading information but also by undermining the very foundations of democracy. The recent advance of generative artificial intelligence has further exacerbated the challenge of distinguishing genuine news from fabricated stories. In response to this challenge, we introduce VeraCT Scan, a novel retrieval-augmented system for fake news detection. This system operates by extracting the core facts from a given piece of news and subsequently conducting an internet-wide search to identify corroborating or conflicting reports. Then sources’ credibility is leveraged for information verification. Besides determining the veracity of news, we also provide transparent evidence and reasoning to support its conclusions, resulting in the interpretability and trust in the results. In addition to GPT-4 Turbo, Llama-2 13B is also fine-tuned for news content understanding, information verification, and reasoning. Both implementations have demonstrated state-of-the-art accuracy in the realm of fake news detection.

2020

pdf bib
Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack
Keqing He | Jinchao Zhang | Yuanmeng Yan | Weiran Xu | Cheng Niu | Jie Zhou
Proceedings of the 28th International Conference on Computational Linguistics

Zero-shot slot filling has widely arisen to cope with data scarcity in target domains. However, previous approaches often ignore constraints between slot value representation and related slot description representation in the latent space and lack enough model robustness. In this paper, we propose a Contrastive Zero-Shot Learning with Adversarial Attack (CZSL-Adv) method for the cross-domain slot filling. The contrastive loss aims to map slot value contextual representations to the corresponding slot description representations. And we introduce an adversarial attack training strategy to improve model robustness. Experimental results show that our model significantly outperforms state-of-the-art baselines under both zero-shot and few-shot settings.

pdf bib
Diversifying Dialogue Generation with Non-Conversational Text
Hui Su | Xiaoyu Shen | Sanqiang Zhao | Zhou Xiao | Pengwei Hu | Randy Zhong | Cheng Niu | Jie Zhou
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation. As bland and generic utterances usually dominate the frequency distribution in our daily chitchat, avoiding them to generate more interesting responses requires complex data filtering, sampling techniques or modifying the training objective. In this paper, we propose a new perspective to diversify dialogue generation by leveraging non-conversational text. Compared with bilateral conversations, non-conversational text are easier to obtain, more diverse and cover a much broader range of topics. We collect a large-scale non-conversational corpus from multi sources including forum comments, idioms and book snippets. We further present a training paradigm to effectively incorporate these text via iterative back translation. The resulting model is tested on two conversational datasets from different domains and is shown to produce significantly more diverse responses without sacrificing the relevance with context.

pdf bib
Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence
Xiaoyu Shen | Ernie Chang | Hui Su | Cheng Niu | Dietrich Klakow
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

The neural attention model has achieved great success in data-to-text generation tasks. Though usually excelling at producing fluent text, it suffers from the problem of information missing, repetition and “hallucination”. Due to the black-box nature of the neural attention architecture, avoiding these problems in a systematic way is non-trivial. To address this concern, we propose to explicitly segment target text into fragment units and align them with their data correspondences. The segmentation and correspondence are jointly learned as latent variables without any human annotations. We further impose a soft statistical constraint to regularize the segmental granularity. The resulting architecture maintains the same expressive power as neural attention models, while being able to generate fully interpretable outputs with several times less computational cost. On both E2E and WebNLG benchmarks, we show the proposed model consistently outperforms its neural attention counterparts.

pdf bib
MovieChats: Chat like Humans in a Closed Domain
Hui Su | Xiaoyu Shen | Zhou Xiao | Zheng Zhang | Ernie Chang | Cheng Zhang | Cheng Niu | Jie Zhou
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Being able to perform in-depth chat with humans in a closed domain is a precondition before an open-domain chatbot can be ever claimed. In this work, we take a close look at the movie domain and present a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots. We propose a unified, readily scalable neural approach which reconciles all subtasks like intent prediction and knowledge retrieval. The model is first pretrained on the huge general-domain data, then finetuned on our corpus. We show this simple neural approach trained on high-quality data is able to outperform commercial systems replying on complex rules. On both the static and interactive tests, we find responses generated by our system exhibits remarkably good engagement and sensibleness close to human-written ones. We further analyze the limits of our work and point out potential directions for future work

2019

pdf bib
Incremental Transformer with Deliberation Decoder for Document Grounded Conversations
Zekang Li | Cheng Niu | Fandong Meng | Yang Feng | Qian Li | Jie Zhou
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document. Obviously, document knowledge plays a critical role in Document Grounded Conversations, while existing dialogue models do not exploit this kind of knowledge effectively enough. In this paper, we propose a novel Transformer-based architecture for multi-turn document grounded conversations. In particular, we devise an Incremental Transformer to encode multi-turn utterances along with knowledge in related documents. Motivated by the human cognitive process, we design a two-pass decoder (Deliberation Decoder) to improve context coherence and knowledge correctness. Our empirical study on a real-world Document Grounded Dataset proves that responses generated by our model significantly outperform competitive baselines on both context coherence and knowledge relevance.

pdf bib
Improving Multi-turn Dialogue Modelling with Utterance ReWriter
Hui Su | Xiaoyu Shen | Rongzhi Zhang | Fei Sun | Pengwei Hu | Cheng Niu | Jie Zhou
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Recent research has achieved impressive results in single-turn dialogue modelling. In the multi-turn setting, however, current models are still far from satisfactory. One major challenge is the frequently occurred coreference and information omission in our daily conversation, making it hard for machines to understand the real intention. In this paper, we propose rewriting the human utterance as a pre-process to help multi-turn dialgoue modelling. Each utterance is first rewritten to recover all coreferred and omitted information. The next processing steps are then performed based on the rewritten utterance. To properly train the utterance rewriter, we collect a new dataset with human annotations and introduce a Transformer-based utterance rewriting architecture using the pointer network. We show the proposed architecture achieves remarkably good performance on the utterance rewriting task. The trained utterance rewriter can be easily integrated into online chatbots and brings general improvement over different domains.

pdf bib
Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation
Zhiqiang Liu | Zuohui Fu | Jie Cao | Gerard de Melo | Yik-Cheung Tam | Cheng Niu | Jie Zhou
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Rhetoric is a vital element in modern poetry, and plays an essential role in improving its aesthetics. However, to date, it has not been considered in research on automatic poetry generation. In this paper, we propose a rhetorically controlled encoder-decoder for modern Chinese poetry generation. Our model relies on a continuous latent variable as a rhetoric controller to capture various rhetorical patterns in an encoder, and then incorporates rhetoric-based mixtures while generating modern Chinese poetry. For metaphor and personification, an automated evaluation shows that our model outperforms state-of-the-art baselines by a substantial margin, while human evaluation shows that our model generates better poems than baseline methods in terms of fluency, coherence, meaningfulness, and rhetorical aesthetics.

pdf bib
Answer-Supervised Question Reformulation for Enhancing Conversational Machine Comprehension
Qian Li | Hui Su | Cheng Niu | Daling Wang | Zekang Li | Shi Feng | Yifei Zhang
Proceedings of the 2nd Workshop on Machine Reading for Question Answering

In conversational machine comprehension, it has become one of the research hotspots integrating conversational history information through question reformulation for obtaining better answers. However, the existing question reformulation models are trained only using supervised question labels annotated by annotators without considering any feedback information from answers. In this paper, we propose a novel Answer-Supervised Question Reformulation (ASQR) model for enhancing conversational machine comprehension with reinforcement learning technology. ASQR utilizes a pointer-copy-based question reformulation model as an agent, takes an action to predict the next word, and observes a reward for the whole sentence state after generating the end-of-sequence token. The experimental results on QuAC dataset prove that our ASQR model is more effective in conversational machine comprehension. Moreover, pretraining is essential in reinforcement learning models, so we provide a high-quality annotated dataset for question reformulation by sampling a part of QuAC dataset.

2008

pdf bib
Combining Multiple Resources to Improve SMT-based Paraphrasing Model
Shiqi Zhao | Cheng Niu | Ming Zhou | Ting Liu | Sheng Li
Proceedings of ACL-08: HLT

2006

pdf bib
A DOM Tree Alignment Model for Mining Parallel Data from the Web
Lei Shi | Cheng Niu | Ming Zhou | Jianfeng Gao
Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics

2005

pdf bib
Word Independent Context Pair Classification Model for Word Sense Disambiguation
Cheng Niu | Wei Li | Rohini K. Srihari | Huifeng Li
Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005)

2004

pdf bib
Weakly Supervised Learning for Cross-document Person Name Disambiguation Supported by Information Extraction
Cheng Niu | Wei Li | Rohini K. Srihari
Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)

pdf bib
Context clustering for Word Sense Disambiguation based on modeling pairwise context similarities
Cheng Niu | Wei Li | Rohini K. Srihari | Huifeng Li | Laurie Crist
Proceedings of SENSEVAL-3, the Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text

2003

pdf bib
Bootstrapping for Named Entity Tagging Using Concept-based Seeds
Cheng Niu | Wei Li | Jihong Ding | Rohini K. Srihari
Companion Volume of the Proceedings of HLT-NAACL 2003 - Short Papers

pdf bib
A Bootstrapping Approach to Named Entity Classification Using Successive Learners
Cheng Niu | Wei Li | Jihong Ding | Rohini Srihari
Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics

pdf bib
An Expert Lexicon Approach to Identifying English Phrasal Verbs
Wei Li | Xiuhong Zhang | Cheng Niu | Yuankai Jiang | Rohini K. Srihari
Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics

pdf bib
InfoXtract location normalization: a hybrid approach to geographic references in information extraction
Huifeng Li | K. Rohini Srihari | Cheng Niu | Wei Li
Proceedings of the HLT-NAACL 2003 Workshop on Analysis of Geographic References

pdf bib
InfoXtract: A Customizable Intermediate Level Information Extraction Engine
Rohini K. Srihari | Wei Li | Cheng Niu | Thomas Cornell
Proceedings of the HLT-NAACL 2003 Workshop on Software Engineering and Architecture of Language Technology Systems (SEALTS)

pdf bib
Question Answering on a Case Insensitive Corpus
Wei Li | Rohini Srihari | Cheng Niu | Xiaoge Li
Proceedings of the ACL 2003 Workshop on Multilingual Summarization and Question Answering

2002

pdf bib
Extracting Exact Answers to Questions Based on Structural Links
Wei Li | Rohini K. Srihari | Xiaoge Li | M. Srikanth | Xiuhong Zhang | Cheng Niu
COLING-02: Multilingual Summarization and Question Answering

pdf bib
Location Normalization for Information Extraction
Huifeng Li | Rohini K. Srihari | Cheng Niu | Wei Li
COLING 2002: The 19th International Conference on Computational Linguistics