Papers by Tuo Zhao

25 papers
BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering (2024.emnlp-main)

Copied to clipboard

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

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

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

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

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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations