Papers by Zuozhu Liu

34 papers
DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have emerged as prominent foundation models for diverse applications due to their outstanding ability to understand and generate humanlike text.
Approach: They propose a dynamic decision-making framework that categorizes tasks into two distinct pathways: 'Fast' and 'Slow' they propose 'self-consistency' strategy to replace the straight-forward decoding method used in COT prompting .
Outcome: The proposed method achieves more than 3% increase in accuracy with lower cost on five popular reasoning benchmarks.
Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework (2022.emnlp-main)

Copied to clipboard

Challenge: Existing supervised sentence embedding techniques rely on expensive human-annotated sentence pairs as the supervised signals.
Approach: They propose a semi-supervised sentence embedding framework that leverages large-scale unlabeled data.
Outcome: The proposed framework surpasses state-of-the-art methods on four domain adaptation tasks.
Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation (2020.emnlp-main)

Copied to clipboard

Challenge: AMR-to-text generation is used to transduce Abstract Meaning Representation structures (AMRs) Graph Convolution Networks (GCNs) are not able to capture non-local information and follow a local (first-order) information aggregation scheme.
Approach: They propose a dynamic fusion mechanism that captures richer non-local interactions . they propose weight tied convolutions and group graph convolution to reduce memory usage .
Outcome: The proposed model outperforms state-of-the-art models on two benchmark datasets with significantly fewer parameters while maintaining the model capacity.
Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level (2024.emnlp-main)

Copied to clipboard

Challenge: General-purpose Large Language Models (LLMs) like GPT-4 have exhibited strong translation abilities.
Approach: They propose to use a model-agnostic model to refine the performance of general-purpose large-language models for machine translation (MT) by utilizing Gemma-2B/7B as the backbone.
Outcome: The proposed model-agnostic and cost-effective tool improves the performance of general-purpose large-language models for machine translation (MT) by integrating it with any general-use LLM.
MT3: A Synergistic Multi-Task RL Framework for Specializing MLLMs in Text Image Machine Translation (2026.acl-long)

Copied to clipboard

Challenge: Text Image Machine Translation (TIMT) is a critical subfield of machine translation . it requires accurate optical character recognition, robust visual-text reasoning, and high-quality translation a challenge .
Approach: They propose a multi-task optimization framework to specialize MLLMs into expert TIMT models.
Outcome: The proposed model outperforms baselines on the latest in-domain MIT-10M benchmark.
Towards Proactive Personalization through Profile Customization for Individual Users in Dialogues (2026.findings-acl)

Copied to clipboard

Challenge: Existing alignment methods focus on universal human values or static, single-turn preferences, thereby failing to address the critical needs of long-term personalization and the initial user cold-start problem.
Approach: They propose a user-centric lifelong agent that continuously infers and adapts to user preferences.
Outcome: The proposed agent achieves superior performance over strong prompt-based and policy optimization baselines, not only in idealized but also in noisy conversational contexts.
Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding (2025.acl-short)

Copied to clipboard

Challenge: Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored.
Approach: They propose a positional contrast decoding technique that contrasts long-aware attention with designed local-awn attention.
Outcome: The proposed model achieves state-of-the-art performance on long-context benchmarks.
TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). human evaluations reveal that LLM-generated translations still contain various errors.
Approach: They propose a LLM-based self-refinement framework that feeds error information back into LLMs to facilitate self-finement, leading to enhanced translation quality.
Outcome: The proposed framework outperforms internal refinement and feedback methods while ensuring a robust translation quality baseline.
MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling (2025.findings-emnlp)

Copied to clipboard

Challenge: MT-RewardTree provides a framework for constructing, evaluating, and deploying process reward models in machine translation (MT)
Approach: They propose a method for automatically generating token-level preference pairs using approximate Monte Carlo Tree Search.
Outcome: The proposed framework achieves state-of-the-art performance in token-level evaluation and sequence-level analysis.
VPL: Visual Proxy Learning Framework for Zero-Shot Medical Image Diagnosis (2024.findings-emnlp)

Copied to clipboard

Challenge: Insufficient medical text precision and the modal disparity between text and vision spaces pose challenges for vision-language models like CLIP.
Approach: They propose a visual proxy learning framework that combines a text refinement module and a stable Sinkhorn algorithm to enhance the diagnostic performance.
Outcome: The proposed model outperforms the state-of-the-art CLIP inference by 1.69% to 15.31% on five datasets covering various diseases.
HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for medical vision-language models overlook modality misalignment . HSCR generates high-quality preference data with higher sampling probability .
Approach: They propose a hierarchical self-contrastive reward approach that addresses two challenges in alignment . they leverage the inherent capability of Med-VLMs to generate dispreferred responses .
Outcome: The proposed approach improves accuracy and trustworthiness of medical vision-label models with 2,000 training entries.
Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for aligning language models with human preferences rely on reward signals and additional annotated data, limiting their scalability and adaptability to diverse human values.
Approach: They propose a discriminative paradigm that leverages the intrinsic preference judgment capabilities of the model to align language models with human preferences.
Outcome: The proposed model is scalable and efficient, paving the way for more adaptive personalized alignment.
Bootstrapped Unsupervised Sentence Representation Learning (2021.acl-long)

Copied to clipboard

Challenge: Existing approaches to learn sentence representations rely on quality labeled data.
Approach: They propose a Siamese Network which maximizes similarity between two augmented views of each sentence.
Outcome: The proposed method outperforms state-of-the-art methods on STS and classification tasks.
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: Large-scale reinforcement learning (RL) methods have proven effective in enhancing the reasoning abilities of large language models.
Approach: They propose an open-source adaptation of the R1-Zero RL framework for machine translation (MT) their code is available at https://github.com/fzp0424/MT-R1-zero.
Outcome: The proposed framework surpasses towerinstruct-7B-v0.2 on the english-chinese benchmark by 1.26 points.
FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering (2025.findings-acl)

Copied to clipboard

Challenge: Existing prompt-based debiasing methods exhibit instability due to sensitivity to prompt changes . fine-tuning-based techniques incur substantial computational overhead and catastrophic forgetting .
Approach: They propose a debiasing framework that encodes fairness-related features into separable directions in the hidden activation space.
Outcome: The proposed framework performs inference-time debiasing without requiring retraining or prompt design . it detects bias signatures in activations and then computes debiased steering vectors . the proposed framework is available to download in the u.s.
Empirical Study of Zero-Shot NER with ChatGPT (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have been a key component of natural language processing (NLP) .
Approach: They propose to decompose the NER task into simpler subproblems by labels and propose a syntactic augmentation strategy to stimulate model's intermediate thinking.
Outcome: The proposed methods achieve remarkable improvements for zero-shot NER across seven benchmarks, including Chinese and English datasets.
LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks for long-form generation assess real-world queries with hard-to-verify metrics or use synthetic setups that overlook real-life intricacies.
Approach: They propose a new approach that balances verifiable and real-world assessment with Target-Anchored Evaluation.
Outcome: The proposed model balances real-world and verifiable assessment with Target-Anchored Evaluation (TAE) it generates queries, textual materials, and anchors based on verifier targets within real-life scenarios .
Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in multimodal large language models have seen remarkable progress for medical decision-making, however, they are designated for specific classification or generative tasks and require model training or finetuning on large-scale datasets with sizeable parameters and tremendous computing.
Approach: They propose a framework that tackles discriminative and generative multimodal medical tasks using multimodal alignment, instruction tuning and routing.
Outcome: The proposed model can achieve superior performance to or on par with state-of-the-art baselines while only requiring 30%-50% of activated model parameters.
Act as you think: Reinforcing Consistent Reasoning in Medical Visual Question Answering (2026.acl-long)

Copied to clipboard

Challenge: Recent advances have improved the accuracy of medical visual question answering (Med-VQA) however, the high stakes nature of the medical domain has precipitated a shift towards interpretability and transparency of reasoning processes.
Approach: They propose a reinforcement learning from verifiable rewards framework that rewards internal consistency and logical coherence.
Outcome: The proposed framework rewards internal consistency and logical coherence, and is highly versatile, the authors show.
An Unsupervised Sentence Embedding Method by Mutual Information Maximization (2020.emnlp-main)

Copied to clipboard

Challenge: Sentence BERT is inefficient for sentence-pair tasks as it needs to evaluate combinatorially many sentence pairs which is very time-consuming.
Approach: They propose a lightweight extension on top of BERT and a self-supervised learning objective to derive meaningful sentence embeddings in an unsupervised manner.
Outcome: The proposed method outperforms baselines on common semantic textual similarity tasks and downstream supervised tasks and achieves performance competitive with supervised methods on various tasks.
Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering (2025.acl-short)

Copied to clipboard

Challenge: Current approaches generate visual markers for all questions, generating excessive visual markers.
Approach: They propose a plug-and-play approach that adapts to the complexity of questions . they propose combining fast intuitive judgments with deliberate analytical reasoning .
Outcome: The proposed approach improves performance on four benchmarks on ScienceQA, TextQA, VizWiz, and MME.
DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition (2025.emnlp-main)

Copied to clipboard

Challenge: Existing datasets designed for Named Entity Recognition methods are inadequate for LLMs.
Approach: They propose a dataset that is multilingual and multi-granular and enables LLMs to be applied to Named Entity Recognition methods.
Outcome: The proposed dataset is multilingual and multi-granular, covering 8 languages and 155 entity types, with corpora spanning a diverse range of domains.
Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models (2024.naacl-short)

Copied to clipboard

Challenge: Existing studies exploring the performance of large language models on named entity recognition tasks have focused on training task-specific LLMs for NER.
Approach: They propose a training-free self-improving framework that utilizes an unlabeled corpus to stimulate the self-learning ability of LLMs.
Outcome: The proposed framework improves performance on the named entity recognition task by using an unlabeled corpus.
How Well Do Text Embedding Models Understand Syntax? (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing text embedding models have not addressed syntactic understanding challenges, highlighting ineffectiveness and enhancing generalization ability.
Approach: They propose to examine the ability of text embedding models to generalize across syntactic contexts.
Outcome: The proposed models exhibit high similarity socres at this simple task.
BiasGuard: A Reasoning-Enhanced Bias Detection Tool for Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for identifying bias in LLM-generated content face limitations . existing methods rely on pattern-based learning, which makes it challenging to understand intentions .
Approach: They propose a bias detection tool that explicitly analyzes inputs and reasons through fairness specifications to provide accurate judgments.
Outcome: The proposed tool outperforms existing tools and improves accuracy and reduces over-fairness misjudgments.
MedCoT: Medical Chain of Thought via Hierarchical Expert (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for medical visual question answering lack robustness and reasoning paths for real-world medical diagnostics.
Approach: They propose a hierarchical expert verification reasoning chain method to enhance interpretability and accuracy in medical visual question answering.
Outcome: The proposed method outperforms existing methods on four standard Med-VQA datasets.
Identifying and Mitigating Social Bias Knowledge in Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Existing methods for debiasing may generate incorrect or nonsensical predictions but leave aside individual commonsense facts, resulting in modified knowledge that elicits unreasonable or undesired predictions.
Approach: They propose a framework that identifies encoding locations of biases within language models and then applies the Fairness-Stamp (FAST) they also propose 'BiaScope' to evaluate the retention of commonsense knowledge and generalization across paraphrased social biase.
Outcome: The proposed framework surpasses state-of-the-art baselines with superior debiasing performance while not compromising the overall model capability for knowledge retention and prediction.
DiffPO: Diffusion-styled Preference Optimization for Inference Time Alignment of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Inference-time alignment approaches still face limitations due to policy-specific value functions and latency during the inference phase.
Approach: They propose an efficient and policy-agnostic preference optimization method that avoids time latency associated with token generation.
Outcome: The proposed method achieves a favorable trade-off between alignment quality and inference-time latency.
BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Existing evaluation approaches rely on fixed-form outputs and cannot adapt to flexible open-text generation scenarios.
Approach: They propose a plug-and-play tool to detect social bias in open-text LLMs.
Outcome: Extensive experiments show that BiasAlert outperforms state-of-the-art methods in detecting bias in open-text generation scenarios.
iPET: An Interactive Emotional Companion Dialogue System with LLM-Powered Virtual Pet World Simulation (2025.acl-demo)

Copied to clipboard

Challenge: Existing approaches to role-playing emotional companion products lack sustained personalization and contextual adaptability, limiting their effectiveness in real-world settings.
Approach: They propose a virtual pet agent that can enhance user engagement through rich, dynamic pet behaviors and interactions tailored to individual preferences.
Outcome: The proposed system has been deployed in a real-world, non-commercial product for 200 days and has demonstrated its effectiveness in practical applications.
Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing methods for video temporal grounding suffer from limited temporal awareness and poor generalization.
Approach: They propose a two-stage training framework that integrates supervised fine-tuning with reinforcement learning to improve both the accuracy and robustness of VTG models.
Outcome: The proposed training framework outperforms existing models on multiple benchmarks on open-domain and challenging scenarios.
Learnable Privacy Neurons Localization in Language Models (2024.acl-short)

Copied to clipboard

Challenge: Large Language Models (LLMs) memorize and disclose private information, especially Personally Identifiable Information (PII) concerns regarding privacy and security within human society remain poorly understood.
Approach: They propose to use learnable binary weight masks to localize PII-sensitive neurons within LLMs by deactivating localized privacy neurons.
Outcome: The proposed method localizes PII-sensitive neurons across all layers and shows the property of PI I specificity.
MedThink: A Rationale-Guided Framework for Explaining Medical Visual Question Answering (2025.findings-naacl)

Copied to clipboard

Challenge: Existing models for medical visual question answering are limited in their interpretation and interpretation . a semi-automated annotation process is used to streamline data preparation and build new benchmark datasets .
Approach: They propose a semi-automated annotation process to streamline data preparation and build new benchmark Med-VQA datasets.
Outcome: The proposed method achieves an accuracy of 83.5% on R-RAD, 86.3% on RSLAKE and 87.2% on RPath.
M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have shown their potential to deliver human-like judgments.
Approach: They propose a systematic LLM-based multi-agent framework for advanced LLM as-a-judge MT evaluation that integrates dimension-specific results into a final evaluation judgment.
Outcome: The proposed framework outperforms existing LLM-as-a-judge methods and competes with state-of-the-art automatic metrics even when powered by a suboptimal model like GPT-4o mini.

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