Papers by Yuxiang Wu

19 papers
Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets (2022.acl-long)

Copied to clipboard

Challenge: Natural language processing models exploit spurious correlations between features and labels in datasets to perform well only within the distributions they are trained on.
Approach: They propose to generate a debiased version of a dataset and replace it with training data to train a model that is generalised to different task distributions.
Outcome: The proposed method outperforms or performs comparable to state-of-the-art debiasing strategies on a large suite of debiased, out-of distribution, and adversarial test sets.
RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation (2026.acl-long)

Copied to clipboard

Challenge: Existing RS agents built on general-purpose LLMs are domain-agnostic, resulting in brittle and error-prone workflows.
Approach: They propose a knowledge-enhanced memory evolution mechanism that bootstraps RS agents with pre-distilled domain knowledge and iteratively integrates online experience for robust multi-step tool execution.
Outcome: Experiments show that the new model improves tool-use performance and accuracy . iteratively, iteration of the model integrates online experience for robust multi-step tool execution .
Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints (2021.acl-short)

Copied to clipboard

Challenge: Adaptive Computation (AC) has been shown to be effective in improving the efficiency of Open-Domain Question Answering systems.
Approach: They propose an AC method that can be applied to an existing ODQA model and can be trained efficiently on a single GPU.
Outcome: The proposed method improves upon a state-of-the-art model on two datasets and is more accurate than previous AC methods due to the stronger base ODQA model.
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them (2021.tacl-1)

Copied to clipboard

Challenge: Open-domain Question Answering models that directly leverage question-answer (QA) pairs show promise in terms of speed and memory compared with conventional models which retrieve and read from text corpora.
Approach: They propose a question-answer (QA)-pair retriever to facilitate improved QA-patch models by introducing Probably Asked Questions (PAQ) they propose QA pair retriever, RePAQ, which preempts and caches test questions, enabling it to match the accuracy of recent retrieve-and-read models, whilst being significantly faster.
Outcome: The proposed model outperforms baseline models by 5% but trails RePAQ by 15% . it can be configured for size (under 500MB) or speed (over 1K questions per second) while retaining high accuracy.
Using Natural Language Explanations to Improve Robustness of In-context Learning (2024.acl-long)

Copied to clipboard

Challenge: Recent studies show that large language models excel in many tasks via in-context learning (ICL). However, ICL struggles to execute complex tasks such as arithmetic, commonsense, and symbolic reasoning.
Approach: They propose to augment ICL with natural language explanations (NLEs) to produce further NLEs on adversarial datasets.
Outcome: The proposed approach yields more accurate results than zero-shot-ICL and using only human-generated NLEs on eight adversarial datasets.
Does the Generator Mind Its Contexts? An Analysis of Generative Model Faithfulness under Context Transfer (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies have focused on examining hallucinations stemming from static input, such as in summarization or machine translation.
Approach: They propose a knowledge-augmented generator that produces information that remains grounded in contextual knowledge regardless of alterations in the context.
Outcome: The proposed method is designed to produce information that remains grounded in contextual knowledge, regardless of alterations in the context.
Zero-shot Event Detection Using a Textual Entailment Model as an Enhanced Annotator (2024.lrec-main)

Copied to clipboard

Challenge: Recent work proposed to use a pre-trained textual entailment model for event detection . but, those methods treated the TE model as a frozen annotator .
Approach: They propose to use TE models to annotate large-scale unlabeled text and annotated data to fine-tune the TE model.
Outcome: The proposed method outperforms baseline methods by 15% on the ACE05 dataset.
MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to voice imitation use complex model design and a quality ceiling when synthetic speech is used as training *sources*.
Approach: They propose a model that uses synthetic speech as training *sources* while retaining real recordings as *targets*.
Outcome: The proposed model outperforms existing methods in naturalness while maintaining competitive similarity scores across speaker identity, accent, and emotion dimensions.
Language Models as Knowledge Bases? (D19-1)

Copied to clipboard

Challenge: Recent advances in pretraining language models on large textual corpora led to a surge of improvements for downstream NLP tasks.
Approach: They present a method for pretraining language models on large textual corpora . they find that they can store relational knowledge and answer queries structured as "fill-in-the-blank" queries.
Outcome: The proposed language models can recall factual knowledge without fine-tuning without fine tuning . the proposed models can answer queries structured as "fill-in-the-blank" cloze statements .
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization (2026.findings-acl)

Copied to clipboard

Challenge: Existing large vision-language model (LVLM) approaches overlook a common strategy used by humans — using maps.
Approach: They propose a method to equip a vision-language model with the ability to think with maps and optimize it using agentic reinforcement learning and parallel test-time scaling.
Outcome: The proposed method outperforms open- and closed-source models on most metrics.
Semantic Parsing by Large Language Models for Intricate Updating Strategies of Zero-Shot Dialogue State Tracking (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for zero-shot Dialogue State Tracking have focused on domaintransfers and have not yielded satisfactory results.
Approach: They propose a new In-Context Learning method to introduce additional updating strategies in zero-shot DST by leveraging powerful Large Language Models and translating the original dialogue to JSON through semantic parsing as an intermediate state.
Outcome: The proposed method outperforms existing zero-shot DST methods on MultiWOZ, showing significant improvements in JGA and slot accuracy compared to existing methods.
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to managing working memory are based on external mechanisms that lack awareness of the agent’s reasoning state, leading to suboptimal decisions.
Approach: They propose a framework that treats working memory management as learnable policy actions and enables joint optimization of information retention and task performance through end-to-end reinforcement learning.
Outcome: The proposed framework matches models 16 larger while reducing average context length by 51%, with learned strategies that adapt to model capabilities and generalize across task complexities.
From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation (2025.acl-long)

Copied to clipboard

Challenge: Traditional generation methods focus primarily on textual quality, but they fail to meet complex, multifaceted educational requirements.
Approach: They propose a method for automatic generating high-quality mathematical problems that align with educational objectives using a dataset of 16k mathematical questions with multi-dimensional educational objectives.
Outcome: The proposed method improves generating high-quality mathematical questions that meet multi-dimensional educational objectives.
An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods rely on parametric models that store knowledge in parameters or retrieval-augmented models that have access to external knowledge sources.
Approach: They propose a parametric parametric model that stores knowledge in its parameters or a retrieval-augmented model that has access to external knowledge sources.
Outcome: The proposed method runs substantially faster across the board and produces more accurate results on WoW and ELI5.
PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks (2022.coling-1)

Copied to clipboard

Challenge: Neural networks are vulnerable to adversarial examples, i.e., under a black-box scenario.
Approach: They propose a word-level search algorithm that searches for subareas under dynamic search space following the subarea importance.
Outcome: The proposed algorithm can achieve comparable success rates to complex search methods while saving numerous queries and time.
Analysing The Impact of Sequence Composition on Language Model Pre-Training (2024.acl-long)

Copied to clipboard

Challenge: Existing studies show that pretraining sequence composition strategy can lead to distracting information from previous documents.
Approach: They propose to use a sequence construction method to concatenate documents into fixed-length sequences to compute the likelihood of each token given its context.
Outcome: The proposed method can improve in-context learning, knowledge memorisation and context utilisation without sacrificing efficiency.
MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for answering time-sensitive questions lack temporal reasoning . existing methods struggle with these time-intensive questions, authors say .
Approach: They propose a temporal-based question-answering framework that integrates temporal perturbations and gold evidence labels into a question processing framework.
Outcome: The proposed framework outperforms baseline retrieval methods in retrieval performance.
Don’t Read Too Much Into It: Adaptive Computation for Open-Domain Question Answering (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to Open-Domain Question Answering assume all passages are of equal importance and allocate computation to them.
Approach: They propose to use adaptive computation to control the computational budget allocated for the passages to be read.
Outcome: The proposed approach reduces computational cost by 4.3x over strong static and adaptive methods while retaining 95% performance of the full model.
TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles (2026.acl-long)

Copied to clipboard

Challenge: Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints.
Approach: They propose a framework that uses tiny language models to evaluate instruction following . they propose to use a set of specialized tiny language model to provide rewards for soft constraints.
Outcome: The proposed framework outperforms baseline models by 12% and speeds up training time by 3.

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