Papers by Siyu Wu

10 papers
Learning from Adjective-Noun Pairs: A Knowledge-enhanced Framework for Target-Oriented Multimodal Sentiment Classification (2022.coling-1)

Copied to clipboard

Challenge: Existing methods to determine sentiment polarity of opinion target are inconsistent and lack visual attention.
Approach: They propose a framework which can exploit adjective-noun pairs extracted from images to improve visual attention and sentiment prediction capability of the TMSC task.
Outcome: The proposed framework outperforms state-of-the-art on two public datasets.
Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing (2025.findings-acl)

Copied to clipboard

Challenge: Role-playing Agents (RPAs) struggle to recognize and respond to hard queries that conflict with their role-play knowledge.
Approach: They propose a lightweight representation editing approach that conveniently shifts conflicting requests to the rejection region, thereby enhancing the model’s refusal accuracy.
Outcome: The proposed model improves RPAs’ refusal ability of conflicting requests while maintaining their general role-playing capabilities.
CIKT: A Collaborative and Iterative Knowledge Tracing Framework with Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Knowledge Tracing (KT) aims to model a student’s learning state over time and predict their future performance.
Approach: They propose a framework that harnesses Large Language Models to enhance both prediction accuracy and explainability by a synergistic optimization loop.
Outcome: The proposed framework improves both prediction accuracy and explainability by using a synergistic optimization loop.
Pre3: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for structured generation of outputs are inefficient under large inference batches.
Approach: They propose a new LLM-based method that parses LR(1) grammars into a pushdown automaton and exploits deterministic pushdown automation to optimize the constrained LLM decoding efficiency.
Outcome: The proposed method improves time per output token (TPOT) by 40% and throughput by 36% .
Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have limitations when it comes to comprehending and expressing world knowledge that extends beyond the boundaries of natural language.
Approach: They propose a model that integrates symbolic data into LLM training without loss of generality ability.
Outcome: The proposed model performs better on symbol- and NL-centric tasks.
MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing defenses target single-turn attacks, but real-world usage involves multi-turn dialogues, exposing models to attacks that exploit conversational context to bypass safety measures.
Approach: They propose a framework that tackles multi-turn jailbreaks from both attack and defense angles.
Outcome: Experiments on large language models show that MUSE effectively mitigates multi-turn jailbreaks.
Diagnose, Then Repair: A Two-Stage MQM-Guided Post-Editing Framework for Domain-Specific Machine Translation (2026.acl-industry)

Copied to clipboard

Challenge: In practice, LLMs are largely diagnostic, with the signals rarely translating into direct quality improvements under real production constraints.
Approach: They propose a two-stage, evaluator-guided automatic post-editing framework that turns MQM-style evaluation into targeted repairs.
Outcome: The proposed framework improves both COMET and CometKiwi scores over one-stage evaluation methods while severities and error spans show strong agreement with human annotations and human editor preferences.
A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Inductive reasoning is an important task for large language models (LLMs).
Approach: They propose a survey of inductive reasoning for large language models . they categorize methods into three main areas: post-training enhancement, test-time exploration, and data augmentation.
Outcome: The proposed method improves inductive reasoning in large language models.
Graph Enhanced Cross-Domain Text-to-SQL Generation (D19-53)

Copied to clipboard

Challenge: Existing deep learning approaches for semantic parsing do not generalize to unseen data sets . existing benchmarks have shown text-to-SQL parsers do not generally perform well to unsen SQL queries.
Approach: They propose a new cross-domain learning scheme to perform text-to-SQL translation . they demonstrate its use on a large-scale cross- domain text- to-Sql data set Spider .
Outcome: The proposed learning scheme improves on a large-scale text-to-SQL data set.
From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning (2026.findings-acl)

Copied to clipboard

Challenge: Generative engines (GEs) are replacing ranked links with citation-grounded answers . current methods are unable to accumulate or transfer effective strategies across tasks and engines .
Approach: They propose a multi-agent framework where planning, editing, and fidelity-aware evaluation serve as the execution layer.
Outcome: The proposed framework outperforms heuristic baselines in visibility and citation fidelity on three mainstream engines.

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