Papers by Lu Hui

23 papers
Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies have shown that LLMs struggle to identify the boundaries of their own knowledge and tend to prioritize external information over internal knowledge learned during pre-training.
Approach: They conduct a comprehensive analysis of LLM representation behaviors and demonstrate the significance of using representations in knowledge checking.
Outcome: The proposed classifiers improve performance even when dealing with noisy knowledge databases.
A Table-to-Text Framework with Heterogeneous Multidominance Attention and Self-Evaluated Multi-Pass Deliberation (2023.findings-emnlp)

Copied to clipboard

Challenge: Table-to-text works have been widely applied in different domains, such as weather forecast and financial report generation.
Approach: They propose a table-to-text approach on top of Self-evaluated multi-pass Generation and Heterogenous Multidominance Attention to explore the hierarchical structure.
Outcome: The proposed method outperforms several SOTA methods quantitatively and qualitatively on three public datasets.
Improve Dense Passage Retrieval with Entailment Tuning (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for dense retrieval have demonstrated remarkable performance in IR tasks.
Approach: They propose a method to improve the embedding of dense retrievers by using existence claim as a bridge.
Outcome: The proposed method can be plugged into current dense retrieval methods and the results are published in the journal Nature.
Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: Efficient instruction tuning aims to enhance the ultimate performance of large language models (LLMs) current methods suffer from the curriculum rigidity, resulting in a fixed and potentially sub-optimal learning trajectory.
Approach: a framework for efficient instruction tuning is proposed to address the issue of curriculum rigidity . current methods rely on static heuristic difficulty metrics and fail to adapt to evolving capabilities .
Outcome: Efficient instruction tuning aims to enhance the ultimate performance of large language models . current methods suffer from the curriculum rigidity, resulting in a fixed learning trajectory .
Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)

Copied to clipboard

Challenge: Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries.
Approach: They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored .
Outcome: The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods.
Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach (2022.emnlp-main)

Copied to clipboard

Challenge: Currently, the generalization issues hinder the applicability of neural table-to-text models due to the limited source tables.
Approach: They propose a table-structureaware text generation model with pretrained language model and propose TASD to bridge the gap between the structured table and text input.
Outcome: The proposed model bridges the gap between the structured table and text input and generates accurate and fluent descriptive texts on two public datasets.
SpanMlt: A Span-based Multi-Task Learning Framework for Pair-wise Aspect and Opinion Terms Extraction (2020.acl-main)

Copied to clipboard

Challenge: Aspect terms and opinion terms are key problems of fine-grained aspect-based sentiment analysis.
Approach: They propose a method to extract aspect and opinion terms as pairs from a sentence . they use shared spans to extract the terms under supervision of span boundaries .
Outcome: The proposed method outperforms state-of-the-art methods on both aspects and opinion terms extraction tasks.
LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction (2024.acl-long)

Copied to clipboard

Challenge: In-context learning (ICL) is an emerging ability of large-scale labeled data for document-level event argument extraction (EAE).
Approach: They propose an explicit heuristic-driven demonstration construction approach that emphasizes task heurs in document-level event argument extraction tasks.
Outcome: The proposed method outperforms existing prompting methods and few-shot supervised learning methods on document-level EAE datasets.
Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts (2026.acl-long)

Copied to clipboard

Challenge: Existing multimodal Mixture-of-Experts models accurately perceive image content yet fail in subsequent reasoning . Seeing but not thinking phenomenon is a puzzling phenomenon .
Approach: They propose a routing-guided intervention method that enhances domain expert activation.
Outcome: The proposed method achieves consistent improvements on visual reasoning tasks.
ChildTalk: A Multi-Dialect Chinese Child Speech Corpus with Full-Length Child–Caregiver Conversations for Speech Recognition (2026.findings-acl)

Copied to clipboard

Challenge: Automatic speech recognition (ASR) for children remains challenging due to developmental variability and the scarcity of high-quality corpora.
Approach: They propose a large-scale Chinese child speech corpus that contains 112.5 hours of speech from 498 children and 500 caregivers.
Outcome: The proposed model improves in-domain and cross-domain performance on children's speech.
MultiConIR: Towards Multi-Condition Information Retrieval (2025.findings-emnlp)

Copied to clipboard

Challenge: MultiConIR is a benchmark designed to evaluate retrieval and reranking models under nuanced multi-condition query scenarios.
Approach: They propose a benchmark to evaluate retrieval and reranking models under nuanced multi-condition query scenarios.
Outcome: The proposed benchmark evaluates retrieval and reranking models under nuanced multi-condition query scenarios across five domains.
Deploying Multi-task Online Server with Large Language Model (2025.coling-industry)

Copied to clipboard

Challenge: In the industry, numerous natural language processing tasks are deployed online . traditional approaches tackle each task separately by its own network and pipeline .
Approach: They propose a three-stage multi-task learning framework for large language models . it involves task filtering, fine-tuning on high-resource tasks, and finally fine- tuning on all tasks .
Outcome: The proposed framework reduces up to 90% of overhead while reducing latency and resource usage.
LoRE: Enhancing Search Relevance with Progressive Chain-of-Thought and Preference Alignment (2026.findings-acl)

Copied to clipboard

Challenge: E-commerce search relevance is a critical component of retrieval systems.
Approach: They propose a large-generative model for search relevance that trains reasoning knowledge, multi-modal understanding and rule awareness into three core competencies.
Outcome: The proposed model outperforms GPT-5 in Macro-F1 and achieves 27% online gain.
Advancing SMoE for Continuous Domain Adaptation of MLLMs: Adaptive Router and Domain-Specific Loss (2025.acl-long)

Copied to clipboard

Challenge: Recent studies have explored Continual Instruction Tuning (CIT) in Multimodal Large Language Models (MLLMs), with a primary focus on Task-incremental CIT, where MLLM are required to continuously acquire new tasks.
Approach: They propose a Sparse Mixture of Expert (SMoE) based method for domain-incremental CIT in Multimodal Large Language Models (MLLMs) . they equip the SMoA module with a domain-specific autoregressive loss (DSAL) they establish a new benchmark to evaluate the efficacy of their method .
Outcome: The proposed method outperforms all baselines and is based on a Sparse Mixture of Experts (SMoE) module .
UER: An Open-Source Toolkit for Pre-training Models (D19-3)

Copied to clipboard

Challenge: Existing work on pre-training models have shown that it is important to use a framework to deploy various pre- training models efficiently.
Approach: They propose an assemble-on-demand pre-training toolkit that assembles pre-trained models on demand and encapsulates them with rich modules.
Outcome: The proposed framework can reproduce state-of-the-art models or develop models that remain unexplored.
Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) enhanced with external contexts face challenges in handling imperfect evidence.
Approach: They propose a framework that can balance internal knowledge with external contexts . they propose gating mechanisms and low-rank representation adapters to adjust hidden representations based on a lightweight intervention function .
Outcome: The proposed model can effectively balance internal knowledge with external context, similar to human cognitive processes.
OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Question Answering (2025.findings-emnlp)

Copied to clipboard

Challenge: a new framework for large language models addresses long-text questions . context compression and dynamic retrieval loops sacrifice critical details or incur iterative costs .
Approach: a new framework is proposed to optimize the entire processing workflow . it uses synergistic components to analyzer, organizer and executor to optimize workflow a .
Outcome: OkraLong improves answer accuracy by 5.7%-41.2% and saves 1.3x-4.7x .
Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data (2025.emnlp-main)

Copied to clipboard

Challenge: Existing literature suggests that RAG systems may face privacy issues when the retrieval process involves private data.
Approach: They propose a two-stage synthetic data generation paradigm that uses attributes to preserve contextual information from the original data.
Outcome: The proposed approach preserves key contextual information from the original data while reducing privacy risks.
SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment (2026.findings-acl)

Copied to clipboard

Challenge: Existing sentence embedding methods rely on fixed prompt templates or involve modifications to the model architecture, compromising its generative capabilities.
Approach: They propose a sentence-level direct preference optimization approach that boosts the sentence representations while preserving the generative ability of LLMs.
Outcome: The proposed method improves representations of semantically meaningful vectors without sacrificing generation capability.
Self-Evaluation of Large Language Model based on Glass-box Features (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluation methods rely on external evaluators, focusing on training and prompting strategies, but model-aware glass-box features are overlooked.
Approach: They propose to use model-aware glass-box features to evaluate an LLM's output.
Outcome: The proposed model-aware features are reliable quality indicators for self-evaluation on public benchmarks.
Towards Robust k-Nearest-Neighbor Machine Translation (2022.emnlp-main)

Copied to clipboard

Challenge: k-Nearest-Neighbor Machine Translation (kNN-MT) is a popular research paradigm in machine translation.
Approach: They propose a confidence-enhanced kNN-MT model with robust training to reduce noise . they introduce NMT confidence to refine the modeling of important components of kN-MT .
Outcome: The proposed model improves on four benchmark datasets and is robust to training.
ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference (2022.findings-acl)

Copied to clipboard

Challenge: State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking.
Approach: They propose to fine tune a pretrained encoder-decoder model using document to query generation.
Outcome: The proposed model achieves comparable results to more expensive approaches while being 6.8X faster.
SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for evaluating the perceptual quality of synthetic speech are limited due to the complexity of perceptual quality factors and the diversity of speech generation tasks.
Approach: They propose a new paradigm for enabling large language models to conduct structured speech quality evaluation using a large-scale dataset.
Outcome: The proposed model performs well across tasks and languages.

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