Papers by Ke Duan

6 papers
Static Models, Dynamic World: A Unified Perspective on Temporal Perception in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models are trained on static corpora but deployed in a dynamic world . a foundational tension remains between time and the ability to understand it .
Approach: They formalize temporal queries in an information-theoretic framework based on parametric reachability of temporal premises and answers.
Outcome: The proposed framework formalizes temporal queries in an information-theoretic framework based on parametric reachability of temporal premises and answers . the framework induces four temporal information regimes corresponding to internal reasoning, answer recency, premise anchoring, and genuine world indeterminacy .
CoSQA: 20,000+ Web Queries for Code Search and Question Answering (2021.acl-long)

Copied to clipboard

Challenge: Using deep neural networks to find codes is difficult . we present a dataset that includes 20,604 labels for natural language queries and codes .
Approach: They introduce a contrastive learning method to enhance text-code matching . they find that CoSQA improves the accuracy of code question answering by 5.1% .
Outcome: The proposed method improves the accuracy of code question answering by 5.1% and improves by 10.5% on a CodeBERT model.
PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have impressive capabilities across various domains, including role-playing, creative writing, mathematical reasoning, and coding.
Approach: They propose two methods to improve the model’s adherence to length constraints and copy-paste accuracy without compromising response quality.
Outcome: The proposed methods improve the model’s adherence to length constraints and copy-paste accuracy without compromising response quality.
MdEval: Massively Multilingual Code Debugging (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks primarily focus on Python and are limited in terms of language diversity.
Approach: They propose a multilingual debugging benchmark that includes 3.9K test samples of 20 programming languages and introduces the debug instruction corpora MdEval-Instruct by injecting bugs into the correct multilingual queries and solutions.
Outcome: The proposed benchmark includes 3.9K test samples of 20 programming languages and covers the automated program repair task, bug localization task, and bug identification task.
Typos Correction Training against Misspellings from Text-to-Text Transformers (2024.lrec-main)

Copied to clipboard

Challenge: Existing dense retrieval systems suffer from typoed queries due to mistyping or phonetic typing errors.
Approach: They propose a method that incorporates the spelling correction objective into the DR model and a prompt-based augmentation technique to enhance the alignment of the typoed query and its original query.
Outcome: The proposed model outperforms existing typos-aware training approaches and sophisticated training advanced retrievers.
Disambiguated Lexically Constrained Neural Machine Translation (2023.findings-acl)

Copied to clipboard

Challenge: Current approaches to LCNMT assume that pre-specified lexicon constraints are contextually appropriate.
Approach: They propose a framework that disambiguates constraints based on contexts at first and integrates them into LCNMT.
Outcome: The proposed approach outperforms baseline approaches on benchmark datasets and comprehensive experiments in multiple target constraints.

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