Papers by Tuo Zhao
BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering (2024.emnlp-main)
Copied to clipboard
Haoyu Wang, Ruirui Li, Haoming Jiang, Jinjin Tian, Zhengyang Wang, Chen Luo, Xianfeng Tang, Monica Cheng, Tuo Zhao, Jing Gao
| Challenge: | Retrieval-augmented Large Language Models struggle with complex inputs and noisy knowledge retrieval hindering model effectiveness. |
| Approach: | They propose a query generation method that integrates query generation blending with knowledge filtering to enhance retrieval-augmented LLMs. |
| Outcome: | The proposed approach surpasses state-of-the-art benchmarks on open-domain question answering benchmarks. |
Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models suffer from severe miscalibration for both in-distribution and out-of-difference data due to over-parameterization. |
| Approach: | They propose a regularized method to improve in-distribution and out-of-distance calibrations by using on-manifold regularization and off-manfold regularisation. |
| Outcome: | The proposed method outperforms existing methods for text classification in terms of expectation calibration error, misclassification detection, and OOD detection on six datasets. |
Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach (2021.emnlp-main)
Copied to clipboard
Simiao Zuo, Chen Liang, Haoming Jiang, Xiaodong Liu, Pengcheng He, Jianfeng Gao, Weizhu Chen, Tuo Zhao
| Challenge: | Existing approaches to adversarial regularization treat adversarials and defending players equally, which is undesirable because only the defending player contributes to the generalization performance. |
| Approach: | They propose a method which formulates adversarial regularization as a Stackelberg game and induces a competition between a leader and a follower. |
| Outcome: | The proposed method outperforms existing adversarial regularization baselines on a set of machine translation and natural language understanding tasks. |
RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive performance but face high computational costs and latency, limiting their deployment in resource-constrained settings. |
| Approach: | They propose a robust RAG framework for large language models via Margin-aware Preference Optimization to enhance the accuracy and reliability of SLMs. |
| Outcome: | The proposed framework surpasses state-of-the-art benchmarks on three open-domain question answering tasks. |
Token-wise Curriculum Learning for Neural Machine Translation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of “easy” samples from training data at the early stage of training. |
| Approach: | They propose a token-wise curriculum learning approach that creates sufficient amounts of easy samples from training data. |
| Outcome: | The proposed approach outperforms baselines on five language pairs on low-resource languages. |
Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization (2021.acl-long)
Copied to clipboard
Chen Liang, Simiao Zuo, Minshuo Chen, Haoming Jiang, Xiaodong Liu, Pengcheng He, Tuo Zhao, Weizhu Chen
| Challenge: | 'lottery tickets' can be trained to match the performance of a full model . subnetwork training can also outperform random sampled subnetworks of the same size . |
| Approach: | They propose to train a subnetwork of 'lottery tickets' to match the full model's performance. |
| Outcome: | The proposed model outperforms subnetworks of the same size in a phase transition phenomenon . the proposed model improves single task fine-tuning by 0.9 points on BERT-base and 1.0 points on GLUE large . |
EFUF: Efficient Fine-Grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to eliminate hallucinations require expensive human annotation . hallucination in multimodal large language models poses unique challenges for current research . |
| Approach: | They propose a fine-grained unlearning framework that performs gradient ascent to eliminate hallucinations without paired data. |
| Outcome: | The proposed method reduces hallucinations while preserving quality with modest computational overhead. |
CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data (2022.naacl-main)
Copied to clipboard
| Challenge: | Despite advances in self-supervised learning, there is a lack of models that can effectively capture both intra- and intra-item semantics for semi-structured session data. |
| Approach: | They propose a graph-based transformer model for semi-structured session data that captures both intra- and intra-item semantics. |
| Outcome: | The proposed model outperforms baselines in three session search and entity linking tasks by up to 9%. |
ARCH: Efficient Adversarial Regularized Training with Caching (2021.findings-emnlp)
Copied to clipboard
Simiao Zuo, Chen Liang, Haoming Jiang, Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen, Tuo Zhao
| Challenge: | Existing approaches to regularize models require generating a perturbation for each sample in each epoch. |
| Approach: | They propose an adversarial regularization method where perturbations are generated and cached once every several epochs. |
| Outcome: | The proposed method significantly eases the computational burden (saves up to 70% of computational time) it produces a notably better (in most of the tasks) or comparable model generalization. |
HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to exit pre-trained language models suffer from the limitation that they have to sequentially traverse through all layers prior to the selected exit layer, which degrades their performance. |
| Approach: | They propose a homotopic and adaptive layer skipping fine-tuning method that adaptively selects the layers to skip based on a predefined budget. |
| Outcome: | The proposed method outperforms all state-of-the-art baselines on the GLUE benchmark and shows that it is highly efficient. |
Data Diversity Matters for Robust Instruction Tuning (2024.findings-emnlp)
Copied to clipboard
Alexander Bukharin, Shiyang Li, Zhengyang Wang, Jingfeng Yang, Bing Yin, Xian Li, Chao Zhang, Tuo Zhao, Haoming Jiang
| Challenge: | Recent studies have shown that by curating high quality and diverse instruction tuning datasets, we can significantly improve instruction-following capabilities. |
| Approach: | They propose an algorithm to control diversity and quality of instruction tuning datasets and validate it. |
| Outcome: | The proposed algorithm significantly improves worst and average case performance on large scale instruction tuning datasets. |
Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data (2021.acl-long)
Copied to clipboard
| Challenge: | Existing work focuses on learning deep NER models with weak supervision without any human annotation. |
| Approach: | They propose a framework that can suppress the noise of the weak labels and fine-tune over the strongly labeled data. |
| Outcome: | The proposed framework outperforms existing methods on Named Entity Recognition tasks with weak supervision and weakly labeled data. |
Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for evaluation of dialog systems are expensive and not scalable . a framework for estimating human evaluation scores is proposed to bridge this gap . |
| Approach: | They propose a framework for estimating human evaluation scores based on off-policy evaluation . they use language quality metrics for single-turn response generation given a fixed context . |
| Outcome: | The proposed framework outperforms existing methods in terms of correlation with human evaluation scores. |
Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. |
| Approach: | They propose a transformer variant with mixed attention spans that leverages the attention mechanism to capture long- and short-range dependencies in the sequence. |
| Outcome: | The proposed model can achieve competitive performance to models with full attention while reducing computational cost (75%) |
RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models have strong generalizability, but fine-tuning involves updating all parameters, rendering full fine-uning resource-intensive. |
| Approach: | They propose a parameter-efficient fine-tuning method that updates all pre-trained parameters during inference. |
| Outcome: | The proposed method outperforms baseline methods on five benchmarks across 20 datasets. |
DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment (2025.findings-emnlp)
Copied to clipboard
Rongzhi Zhang, Chenwei Zhang, Xinyang Zhang, Liang Qiu, Haoming Jiang, Yuchen Zhuang, Qingru Zhang, Hyokun Yun, Xian Li, Bing Yin, Tuo Zhao, Chao Zhang
| Challenge: | Existing approaches to align large language models with human preferences are noisy and varying in importance of preference samples. |
| Approach: | a new method enhances reward modeling by learning to dynamically weigh preference data. |
| Outcome: | a new method improves the performance of large language models with human preferences . it initializes data importance and iteratively refines them to maximize validation performance. |
Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach (2021.naacl-main)
Copied to clipboard
| Challenge: | Fine-tuned pre-trained language models (LMs) have enormous success in many natural language processing tasks, but they still require excessive labeled data in the fine-tuning stage. |
| Approach: | They propose a framework to enable fine-tuning pre-trained language models with weak supervision without any labeled data. |
| Outcome: | The proposed framework outperforms the strongest baseline and achieves competitive performance with fully-supervised fine-tuning methods. |
MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for training pre-trained language models have limited practicality due to latency requirements. |
| Approach: | They propose a method that uses a Mixture-of-Experts structure to increase model capacity and inference speed. |
| Outcome: | The proposed method outperforms existing distillation methods on natural language understanding and question answering tasks. |
Self-Training with Differentiable Teacher (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for self-training are interpreted as teacher-student frameworks, where the teacher generates pseudo-labels and the student makes predictions. |
| Approach: | They propose a differentiable self-training method that treats teacher-student as a Stackelberg game where a leader is always in a more advantageous position than a follower. |
| Outcome: | The proposed model outperforms existing methods on semi- and weakly-supervised learning tasks on semi and weak supervised tasks. |
Context-Aware Query Rewriting for Improving Users’ Search Experience on E-commerce Websites (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing query rewriting models ignore user history behaviors and consider only the instant search query, which is often a short string offering limited information about the true shopping intent. |
| Approach: | They propose an end-to-end context-aware query rewriting model that takes search context into account and builds a session graph using the history search queries and their contained words. |
| Outcome: | The proposed model outperforms state-of-the-art models under various metrics. |
OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Existing reward models rely on scalar or pairwise judgments that fail to capture multifaceted nature of human preferences. |
| Approach: | They propose a rubric-based reward model that uses a large collection of prompt, rubric pairs to generate a scalar score or preference label for each response. |
| Outcome: | The proposed model surpasses strong size-matched baselines by 8.4% across multiple benchmarks. |
MessToClean: Evidence-Grounded Structure-Preserving Reconstruction for Real-World Degraded Exam Paper Images (2026.acl-long)
Copied to clipboard
Jiayi Tuo, Cheng Tang, Zihan Wang, Chenyue Zhou, Yao Li, Yanbiao Ma, Chao Wang, Wei Dai, Mingxuan Wang, Shitong Qin, Ziwei Zhao
| Challenge: | Existing Multimodal Large Language Models (MLLMs) fail under RDEI, leading to disrupted structure and evidence-unsupported hallucinations. |
| Approach: | They propose a backbone-agnostic, evidence-driven pipeline that treats off-the-shelf MLLMs as interchangeable components to improve stem consistency and figure consistency. |
| Outcome: | The proposed pipeline improves stem consistency by 1.01-3.18%, figure consistency by 0.50-49.16%, and refusal F1 by 1.06-10.88% across question types. |
CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing (2022.acl-long)
Copied to clipboard
| Challenge: | Existing work has resorted to sharing weights among models, but results are not affordable for real-world deployment. |
| Approach: | They propose a consistency-regularized ensemble learning approach based on perturbed models to retain ensemble benefits while maintaining a low memory cost. |
| Outcome: | The proposed approach outperforms the standard ensemble of 8 BERT-base models on the GLUE benchmark by 0.7 with a significantly smaller model size. |
Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing (2020.acl-main)
Copied to clipboard
| Challenge: | Existing multi-domain neural machine translation models lack adaptation to individual domains. |
| Approach: | They propose a multi-domain neural machine translation model with individual modules for each domain . they use word-level, adaptive and layer-wise domain mixing to achieve this . |
| Outcome: | The proposed model outperforms existing models in several NMT tasks. |
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pre-trained models fail to generalize to unseen data. |
| Approach: | They propose a framework for robust and efficient fine-tuning for pre-trained models . proposed framework achieves new state-of-the-art performance on a number of NLP tasks . |
| Outcome: | The proposed framework outperforms the state-of-the-art T5 model on GLUE, SNLI, SciTail and ANLI. |