Papers by Yuxi Wang

11 papers
Exploring Question-Specific Rewards for Generating Deep Questions (2020.coling-main)

Copied to clipboard

Challenge: Recent question generation approaches use the sequence-to-sequence framework to optimize the log likelihood of ground-truth questions using teacher forcing.
Approach: They propose to optimize for QG-specific objectives via reinforcement learning to improve question quality.
Outcome: The proposed model improves the fluency, relevance, and answerability of generated questions.
Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation (2026.acl-long)

Copied to clipboard

Challenge: Retrieval-Augmented Generation (RAG) provides access to external knowledge, but current research focuses on retrieval quality and 'integration bottleneck' .
Approach: They propose a framework that explicitly decouples reasoning from evidence integration by generating an 'Inner-Answer' and a 'Refer-Aswer" they propose 'a joint decoding mechanism that dynamically fuses the logical coherence of the Inner-Andswer with the factual precision of the Refer-Adswer at the token level'
Outcome: The proposed framework improves accuracy by 12.1% and reduces hallucinations by 16.3% on five QA benchmarks.
Towards Human-aligned Evaluation for Linear Programming Word Problems (2024.lrec-main)

Copied to clipboard

Challenge: Existing evaluation methodologies for MWPs diverge from human judgment and face challenges in recognizing mathematically equivalent answers.
Approach: They propose an evaluation metric rooted in graph edit distance that features benefits such as permutation invariance and more accurate program equivalence identification.
Outcome: The proposed evaluation metric features benefits such as permutation invariance and more accurate program equivalence identification.
MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Current approaches focus on isolated meme analysis, either for harmful content detection or standalone interpretation, overlooking a fundamental challenge: the same meme can express different intents depending on its conversational context.
Approach: They propose a benchmark to evaluate how large vision language models understand memes in their original context.
Outcome: The proposed benchmark evaluates how large vision language models understand meme intent in their original context.
Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Recent efforts have identified adversarial suffixes capable of jailbreaking LLMs . however, GCG struggles with computational inefficiency, limiting further studies .
Approach: They propose a two-stage transfer learning framework which decouples the search process into behavior-agnostic pre-searching and behavior-relevant post-search.
Outcome: The proposed approach outperforms baseline on Llama2-chat-7b with ASRs of 43.9 (+ 22.2) and 39.0 (+ 19.5) on valid and test sets.
AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge (2025.acl-long)

Copied to clipboard

Challenge: Existing studies solve this challenge by updating benchmarks with newly collected data, but they fail to guarantee contamination-free evaluation as the newly collected knowledge may contain pre-existing knowledge.
Approach: They propose an automated anti-leakage benchmarking framework that builds and updates benchmarks without human labor instead of using newly collected data.
Outcome: The proposed framework significantly reduces the cost of benchmark maintenance to accommodate emerging LLMs.
DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing approaches to augment self-training (ST) in attribute-controllable language generation are limited and limited.
Approach: They propose a new ST framework that integrates self-generated pseudo text into attribute-controllable language generation.
Outcome: The proposed framework can be applied to semi-supervised controllable language generation.
Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to condensing textual information into concise and structured tables are limited in their applicability in broader contexts.
Approach: They propose a benchmark dataset for generating summary tables of competitions based on real-time commentary texts that incorporates large-scale textual information into concise and structured tables.
Outcome: The proposed method exhibits strong generalization abilities, surpassing previous approaches on several other text-to-table datasets.
Co-VQA : Answering by Interactive Sub Question Sequence (2022.findings-acl)

Copied to clipboard

Challenge: Existing approaches to Visual Question Answering (VQA) answer questions directly, but people usually decompose a complex question into a sequence of simple sub questions.
Approach: They propose a conversation-based VQA framework that decomposes questions into sub questions and answers them one-by-one.
Outcome: The proposed framework achieves state-of-the-art on VQA 2.0 and VQA-CP v2 datasets.
TexPrax: A Messaging Application for Ethical, Real-time Data Collection and Annotation (2022.aacl-demo)

Copied to clipboard

Challenge: TexPrax is a messaging system to collect and annotate task-oriented dialog data . informal communication channels such as instant messengers are increasingly being used at work .
Approach: They propose a messaging system that collects and annotates task-oriented dialog data from employees via chatbots.
Outcome: The proposed system collects and annotates tasks-oriented dialog data from german factory workers and provides lightweight annotations.
LEDOM: Reverse Language Model (2026.acl-long)

Copied to clipboard

Challenge: Autoregressive language models are trained exclusively left-to-right, yet they are limited in their ability to factorize text.
Approach: They propose a purely reverse autoregressive language model that factorizes text as a product of left-to-right conditionals.
Outcome: The proposed model can be used to score forward outputs using reverse posterior estimates.

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