Tan Yu
Author directoryAlso published as: Tan YU
2026
UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models
Huawei Lin | Yingjie Lao | Tony Geng | Tan YU | Weijie Zhao
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Huawei Lin | Yingjie Lao | Tony Geng | Tan YU | Weijie Zhao
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outputs. In this paper, departing from traditional deep learning attack paradigms, we explore their intrinsic relationship and collectively term them Prompt Trigger Attacks (PTA). This raises a key question: Given a prompt, can we tell whether a hidden trigger is steering the model’s behavior? To address this, we propose UniGuardian, the first unified, training-free defense that detects trigger-activated prompt injection, backdoor, and adversarial attacks by measuring how structured perturbations of the prompt shift the model’s output distribution. Additionally, we introduce a single-forward strategy to optimize the detection pipeline, enabling simultaneous attack detection and text generation within a single forward pass. Our experiments confirm that UniGuardian accurately and efficiently identifies trigger-activated prompts in LLMs.
Adaptive Data Flywheel: Applying MAPE Control Loops to AI Agent Improvement
Aaditya Shukla | Sidney Knowles | Meenakshi Madugula | David Farris | Ryan Angilly | Santiago Pombo | Lu An | Anbang Xu | Abhinav Balasubramanian | Tan Yu | Jiaxiang Ren | Rama Akkiraju
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)
Aaditya Shukla | Sidney Knowles | Meenakshi Madugula | David Farris | Ryan Angilly | Santiago Pombo | Lu An | Anbang Xu | Abhinav Balasubramanian | Tan Yu | Jiaxiang Ren | Rama Akkiraju
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)
Enterprise AI agents must continuously adapt to maintain accuracy, reduce latency, and remain aligned with user needs. We present a practical implementation of a data flywheel in NVInfo AI, NVIDIA’s Mixture-of-Experts (MoE) Knowledge Assistant serving over 30,000 employees. By operationalizing a MAPE-driven data flywheel, we built a closed-loop system that systematically addresses failures in retrieval-augmented generation (RAG) pipelines and enables continuous learning.Over a 3-month post-deployment period, we monitored feedback and collected 495 negative samples. Analysis revealed two major failure modes: routing errors (5.25%) and query rephrasal errors (3.2%). Using NVIDIA NeMo Microservices, we implemented targeted improvements through fine-tuning. For routing, we replaced a Llama 3.1 70B model with a fine-tuned 8B variant, achieving 96% accuracy, a 10× reduction in model size, and 70% latency improvement. For query rephrasal, fine-tuning yielded a 3.7% gain in accuracy and a 40% latency reduction.Our approach demonstrates how human-in-the-loop (HITL) feedback, when structured within a data flywheel, transforms enterprise AI agents into self-improving systems. Key learnings include approaches to ensure agent robustness despite limited user feedback, navigating privacy constraints, and executing staged rollouts in production. This work offers a repeatable blueprint for building robust, adaptive enterprise AI agents capable of learning from real-world usage at scale.
2025
EKRAG: Benchmark RAG for Enterprise Knowledge Question Answering
Tan Yu | Wenfei Zhou | Lei Yang | Aaditya Shukla | Meenakshi Madugula | Pritam Gundecha | Nick Burnett | Anbang Xu | Vishal Seth | Tamar Bar | Rama Akkiraju | Vivienne Zhang
Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing
Tan Yu | Wenfei Zhou | Lei Yang | Aaditya Shukla | Meenakshi Madugula | Pritam Gundecha | Nick Burnett | Anbang Xu | Vishal Seth | Tamar Bar | Rama Akkiraju | Vivienne Zhang
Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing
Retrieval-augmented generation (RAG) offers a robust solution for developing enterprise internal virtual assistants by leveraging domain-specific knowledge and utilizing information from frequently updated corporate document repositories. In this work, we introduce the Enterprise-Knowledge RAG (EKRAG) dataset to benchmark RAG for enterprise knowledge question-answering (QA) across a diverse range of corporate documents, such as product releases, technical blogs, and financial reports. Using EKRAG, we systematically evaluate various retrieval models and strategies tailored for corporate content. We propose novel embedding-model (EM)-as-judge and ranking-model (RM)-as-judge approaches to assess answer quality in the context of enterprise information. Combining these with the existing LLM-as-judge method, we then comprehensively evaluate the correctness, relevance, and faithfulness of generated answers to corporate queries. Our extensive experiments shed light on optimizing RAG pipelines for enterprise knowledge QA, providing valuable guidance for practitioners. This work contributes to enhancing information retrieval and question-answering capabilities in corporate environments that demand high degrees of factuality and context-awareness.
2022
Cross-Lingual Cross-Modal Consolidation for Effective Multilingual Video Corpus Moment Retrieval
Jiaheng Liu | Tan Yu | Hanyu Peng | Mingming Sun | Ping Li
Findings of the Association for Computational Linguistics: NAACL 2022
Jiaheng Liu | Tan Yu | Hanyu Peng | Mingming Sun | Ping Li
Findings of the Association for Computational Linguistics: NAACL 2022
Existing multilingual video corpus moment retrieval (mVCMR) methods are mainly based on a two-stream structure. The visual stream utilizes the visual content in the video to estimate the query-visual similarity, and the subtitle stream exploits the query-subtitle similarity. The final query-video similarity ensembles similarities from two streams. In our work, we pro- pose a simple and effective strategy termed as Cross-lingual Cross-modal Consolidation (C3 ) to improve mVCMR accuracy. We adopt the ensemble similarity as the teacher to guide the training of each stream, leading to a more powerful ensemble similarity. Meanwhile, we use the teacher for a specific language to guide the student for another language to exploit the complementary knowledge across languages. Ex- tensive experiments on mTVR dataset demonstrate the effectiveness of our C3 method.
2021
Cross-lingual Cross-modal Pretraining for Multimodal Retrieval
Hongliang Fei | Tan Yu | Ping Li
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Hongliang Fei | Tan Yu | Ping Li
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Recent pretrained vision-language models have achieved impressive performance on cross-modal retrieval tasks in English. Their success, however, heavily depends on the availability of many annotated image-caption datasets for pretraining, where the texts are not necessarily in English. Although we can utilize machine translation (MT) tools to translate non-English text to English, the performance still largely relies on MT’s quality and may suffer from high latency problems in real-world applications. This paper proposes a new approach to learn cross-lingual cross-modal representations for matching images and their relevant captions in multiple languages. We seamlessly combine cross-lingual pretraining objectives and cross-modal pretraining objectives in a unified framework to learn image and text in a joint embedding space from available English image-caption data, monolingual and parallel corpus. We show that our approach achieves SOTA performance in retrieval tasks on two multimodal multilingual image caption benchmarks: Multi30k with German captions and MSCOCO with Japanese captions.
Inflate and Shrink:Enriching and Reducing Interactions for Fast Text-Image Retrieval
Haoliang Liu | Tan Yu | Ping Li
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Haoliang Liu | Tan Yu | Ping Li
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
By exploiting the cross-modal attention, cross-BERT methods have achieved state-of-the-art accuracy in cross-modal retrieval. Nevertheless, the heavy text-image interactions in the cross-BERT model are prohibitively slow for large-scale retrieval. Late-interaction methods trade off retrieval accuracy and efficiency by exploiting cross-modal interaction only in the late stage, attaining a satisfactory retrieval speed. In this work, we propose an inflating and shrinking approach to further boost the efficiency and accuracy of late-interaction methods. The inflating operation plugs several codes in the input of the encoder to exploit the text-image interactions more thoroughly for higher retrieval accuracy. Then the shrinking operation gradually reduces the text-image interactions through knowledge distilling for higher efficiency. Through an inflating operation followed by a shrinking operation, both efficiency and accuracy of a late-interaction model are boosted. Systematic experiments on public benchmarks demonstrate the effectiveness of our inflating and shrinking approach.
Search
Co-authors
- Ping Li 3
- Rama Akkiraju 2
- Meenakshi Madugula 2
- Aaditya Shukla 2
- Anbang Xu 2
- Lu An 1
- Ryan Angilly 1
- Abhinav Balasubramanian 1
- Tamar Bar 1
- Nick Burnett 1
- David Farris 1
- Hongliang Fei 1
- Tong Geng 1
- Pritam Gundecha 1
- Sidney Knowles 1
- Yingjie Lao 1
- Huawei Lin 1
- Haoliang Liu 1
- Jiaheng Liu 1
- Hanyu Peng 1
- Santiago Pombo 1
- Jiaxiang Ren 1
- Vishal Seth 1
- Mingming Sun 1
- Lei Yang 1
- Vivienne Zhang 1
- Weijie Zhao 1
- Wenfei Zhou 1