Papers by Qingkai Zeng

17 papers
Crossing Variational Autoencoders for Answer Retrieval (2020.acl-main)

Copied to clipboard

Challenge: Existing methods learned semantic representations with dual encoders or dual variational auto-encoders failed to capture the aligned semantics between question and answer.
Approach: They propose to use two variational auto-encoders to generate questions with aligned answers and generating answers with align questions.
Outcome: The proposed method outperforms the state-of-the-art answer retrieval method on SQuAD.
ChatEL: Entity Linking with Chatbots (2024.lrec-main)

Copied to clipboard

Challenge: Entity Linking (EL) is a challenging task in natural language processing . existing approaches focus on creating elaborate contextual models that are unwieldy and difficult to train .
Approach: They propose a framework to prompt LLMs to return accurate results for Entity Linking . they use a three-step framework to generate a set of EL models that can be open-source .
Outcome: The proposed framework improves the average F1 performance across 10 datasets by more than 2%.
Pre-trained Models Perform the Best When Token Distributions Follow Zipf’s Law (2025.emnlp-main)

Copied to clipboard

Challenge: Existing large language models typically fix a vocabulary size in advance, then use Byte Pair Encoding (BPE) to construct the tokenizer.
Approach: They propose a method for determining the vocabulary size by analyzing token frequency distributions through Zipf’s law and propose to use it to optimize model performance.
Outcome: The proposed method improves model efficiency and effectiveness across NLP, genomics, and chemistry.
CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts (2025.findings-acl)

Copied to clipboard

Challenge: Existing taxonomies are mainly constructed by experts or through crowd-sourcing, making the process time-consuming, labor-intensive, and restricted in coverage.
Approach: They propose a method that leverages large language models to capture taxonomic structure . existing taxonomies are mainly constructed by experts or through crowd-sourcing .
Outcome: Experiments on five real-world domains show that CodeTaxo outperforms state-of-the-art methods.
Instant Personalized Large Language Model Adaptation via Hypernetwork (2026.acl-long)

Copied to clipboard

Challenge: Existing parameter-efficient fine-tuning methods require training a separate adapter for each user, making them computationally expensive and impractical for real-time updates.
Approach: They propose a scalable framework that maps a user's profile directly to a full set of adapter parameters.
Outcome: The proposed framework outperforms prompt-based personalization and OPPU while using substantially fewer computational resources at deployment.
Enhancing Mathematical Reasoning in LLMs by Stepwise Correction (2025.acl-long)

Copied to clipboard

Challenge: Existing Best-of-N decoding methods often lead to incorrect solutions . a novel method is proposed to help large language models identify and revise incorrect steps in their generated reasoning paths.
Approach: They propose a method that helps large language models identify and revise incorrect steps in their generated reasoning paths.
Outcome: The proposed method outperforms the state-of-the-art Best-ofN decoding method by +2.4 and reduces token consumption by 77.8%.
Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method (D19-53)

Copied to clipboard

Challenge: faceted concept hierarchy is a structure of parent-child relationships . concepts are expected to be organized in a hierarchical structure for student learning .
Approach: They propose a faceted concept hierarchy that aims to build facets from scientific literature.
Outcome: The proposed hierarchy is more complete than "type-of" relations, and resolves conflicts by maintaining the acyclic structure of a hierarchy.
Technical Question Answering across Tasks and Domains (2021.naacl-industry)

Copied to clipboard

Challenge: Existing methods for technical QA have a limited data size and question and answer overlaps .
Approach: They propose a framework of deep transfer learning to address technical QA across tasks and domains using document retrieval and reading comprehension tasks.
Outcome: The proposed framework performs better than state-of-the-art methods on the TechQA task.
Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench (2025.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) and Multimodal Large Language models (MLLMs) trained on vast web corpora can memorize and disclose individuals’ confidential and private data, raising legal and ethical concerns.
Approach: They propose a benchmark to assess unlearning algorithms from multiple perspectives and provide a baseline for existing generative models.
Outcome: The proposed benchmark consists of 500 fictitious profiles and 153 profiles for public celebrities, evaluated from both multimodal (image+text) and unimodal (text) perspectives.
Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Large language models can perform a wide range of tasks by following natural language instructions without task-specific fine-tuning.
Approach: They propose a method to automatically improve the quality of LLM instructions . they leverage the generative ability of LMS to generate diverse candidate instructions based on a scoring model trained on 575 existing NLP tasks.
Outcome: The proposed method surpasses human-written and LLM-generated instructions on 118 out-of-domain tasks.
From Personal to Collective: On the Role of Local and Global Knowledge in LLM Personalization (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are the backbone of modern AI systems supporting a wide range of applications.
Approach: They propose a Local–Global knowledge framework that augments user-specific signals with a global knowledge encoding collective behavioral trends.
Outcome: The proposed framework outperforms existing methods on five personalization benchmarks.
MinT: Boosting Generalization in Mathematical Reasoning via Multi-view Fine-tuning (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods focus on specializing LMs in mathematical reasoning and rely on knowledge distillation.
Approach: They propose a multi-view fine-tuning method that exploits existing mathematical problem datasets with diverse annotation styles.
Outcome: The proposed method outperforms existing methods that rely heavily on LLM teachers . it grants models generalization ability across views and datasets, and the capability to learn from inaccurate or incomplete data.
Large Language Models Can Self-Correct with Key Condition Verification (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to correct reasoning without external feedback have not been used in large language models.
Approach: They propose an iterative verify-then-correct framework to progressively identify and correct (probably) false responses, named ProCo.
Outcome: The proposed method improves the accuracy of LLMs on three reasoning tasks.
Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning (2024.emnlp-main)

Copied to clipboard

Challenge: Experimental results demonstrate that OPPU significantly outperforms existing prompt-based methods across seven diverse tasks in the LaMP benchmark.
Approach: They propose to integrate parametric user knowledge into the personal PEFT parameters and non-parametric knowledge from retrieval and profiles, adapting LLMs to user behavior shifts.
Outcome: The proposed method outperforms existing prompt-based methods across seven diverse tasks in the LaMP benchmark.
Enhancing Factual Consistency of Abstractive Summarization (2021.naacl-main)

Copied to clipboard

Challenge: Abstractive summarization models often distort or fabricate facts in articles . factual inconsistency is a common problem with abstractive summaries .
Approach: They propose a fact-aware summarization model FASum to extract factual relations into the summary generation process via graph attention.
Outcome: The proposed model can produce abstractive summaries with higher factual consistency compared with existing systems and corrects factual errors via modifying only a few keywords.
A Technical Question Answering System with Transfer Learning (2020.emnlp-demos)

Copied to clipboard

Challenge: StackOverflow and AskUbuntu are popular open forum communities for technical question-answering, but it is expensive for human experts to provide timely and helpful responses.
Approach: They develop a system that automatically responds to questions from a siamese ALBERT network based on previously answered questions .
Outcome: The proposed system responds automatically to questions based on answers from previous users.
Tri-Train: Automatic Pre-Fine Tuning between Pre-Training and Fine-Tuning for SciNER (2020.findings-emnlp)

Copied to clipboard

Challenge: Pre-training a language model by self-supervised tasks on huge datasets and fine-tuning with small labelled data are often inadequate for scientific NER tasks.
Approach: They propose to introduce a "pre-fine tuning" step between pre-training and fine-tuning to construct a corpus by selecting sentences from unlabeled documents that are the most relevant with labelled training data.
Outcome: The proposed approach improves on seven benchmarks on the performance of the proposed model on labelled datasets.

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