Papers by Sijia Wang

19 papers
Targeted Augmentation for Low-Resource Event Extraction (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods for low-resource information extraction struggle to strike a balance between weak augmentation and drastic augmentation.
Approach: They propose a data augmentation paradigm that uses back validation and targeted augmentation to produce augmented examples with enhanced diversity, polarity, accuracy, and coherence.
Outcome: The proposed paradigm produces augmented examples with enhanced diversity, polarity, accuracy, and coherence.
Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for storing key-value caches during long-horizon rollouts cause performance collapses.
Approach: They propose a new training paradigm that empowers stable RL training under sparse rollouts.
Outcome: The proposed model reduces rollout overhead while maintaining the performance.
Self-Guided Function Calling in Large Language Models via Stepwise Experience Recall (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for function calling require expert effort and prompt engineering becomes inefficient.
Approach: They propose a method that performs fine-grained, stepwise retrieval from a continually updated experience pool.
Outcome: The proposed method achieves an average improvement of 6.1% on easy and 4.7% on hard questions.
Ameli: Enhancing Multimodal Entity Linking with Fine-Grained Attributes (2024.eacl-long)

Copied to clipboard

Challenge: Experimental results show that understanding attributes of mentions from text descriptions and visual images plays a vital role in multimodal entity linking.
Approach: They propose to integrate attributes into multimodal entity linking using a text-image-based knowledge base.
Outcome: The proposed approach integrates attributes into disambiguation.
Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding (2022.findings-acl)

Copied to clipboard

Challenge: Existing approaches to event extraction are limited to a set of pre-defined types.
Approach: They propose a natural language query framework that uses event types and argument roles to extract candidate triggers and arguments from input text.
Outcome: The proposed framework outperforms existing methods on zero-shot event extraction.
Detecting Stealthy Backdoor Samples based on Intra-class Distance for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing detectors use classifier-style probability signals or rely on rewriting, which can degrade quality and introduce new triggers.
Approach: They propose to efficiently remove poisoned examples before or during fine-tuning .
Outcome: The proposed method outperforms prior detectors on two machine translation datasets and one QA dataset.
Benchmarking Diverse-Modal Entity Linking with Generative Models (2023.findings-acl)

Copied to clipboard

Challenge: Existing models for diverse-mode entity linking (EL) work well on per modality configurations, but it is more challenging to design a unified model for diverse modality.
Approach: They propose a generative diverse-modal model that integrates text, image and table . they propose combining a multimodal encoder-decoder paradigm with a fine-tuning GDMM .
Outcome: The proposed model outperforms state-of-the-art models by 8.51 F1 on average for diverse-modal EL.
The Art of Prompting: Event Detection based on Type Specific Prompts (2023.acl-short)

Copied to clipboard

Challenge: Experimental results show that a well-defined and comprehensive description of event types can significantly improve event detection performance when the annotations are limited.
Approach: They propose a unified framework to integrate event type specific prompts for supervised, few-shot and zero-shot event detection.
Outcome: The proposed framework shows up to 22.2% gain over the prior state-of-the-art frameworks.
Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Large language models (LLMs) often struggle with the issue of generating inaccurate or fabricated content even when they possess correct knowledge.
Approach: They propose a decoding method that mitigates hallucinations without extra training . they propose entropy eNhanced decoding that leverages inner probability changes .
Outcome: The proposed method improves the truthfulness and informativeness of generation while maintaining robust QA accuracy.
Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for LRM unlearning overlook critical information leakage in reasoning traces, even when final answers are successfully removed.
Approach: They propose a method that suppresses reasoning traces while preserving the model's general reasoning ability.
Outcome: The proposed method significantly reduces reasoning trace leakage and achieves strong performance across reasoning and safety benchmarks, including WMDP, StrongReject, JBB-Behaviors and WildJailbreak.
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Prediction (2022.naacl-main)

Copied to clipboard

Challenge: Existing models are vulnerable to adversarial attacks, but their vulnerability is underexplored.
Approach: They propose to concatenate a perturbed but semantically similar tweet into a model that fools stock prediction models.
Outcome: The proposed method achieves consistent success rates and causes significant monetary loss in trading simulation by simply concatenating a perturbed but semantically similar tweet.
RE2: Region-Aware Relation Extraction from Visually Rich Documents (2024.naacl-long)

Copied to clipboard

Challenge: Existing studies on relation extraction from visually rich documents focus on layout structure and Optical Character Recognition (OCR) results.
Approach: They propose a relation extraction tool that leverages layout structure among entity blocks to improve relation prediction.
Outcome: The proposed model outperforms existing models on a wide range of domains and languages.
Beyond the Surface: A Solution-Aware Retrieval Model for Competition-level Code Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing retrieval models emphasize surface-level semantic similarity, neglecting deeper solution-level logical similarities.
Approach: They propose a solution-aware ranking model empowered by synthetic data for competitive programming tasks.
Outcome: The proposed ranking model outperforms existing retrieval models in precision and recall metrics.
More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Sampling (2024.findings-naacl)

Copied to clipboard

Challenge: Existing studies on LLM prompting focus on selecting a better set of data samples inside one single prompt input, but why not design and leverage multiple ICL prompts together to further improve the LLM’s performance?
Approach: They propose a low-resource LLM prompting technique to optimize the construction of multiple ICL prompt inputs to produce confident predictions.
Outcome: The proposed technique can produce confident predictions by optimizing the construction of multiple ICL prompt inputs on four NLI datasets and one QA dataset.
Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good (P19-1)

Copied to clipboard

Challenge: Persuasion agents are a form of communication that can be used to change people's opinions and actions for social good.
Approach: They designed an online persuasion task where one participant was asked to persult the other to donate to a specific charity.
Outcome: The proposed system could change people's opinions and actions for social good.
SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection (2026.acl-industry)

Copied to clipboard

Challenge: High-quality data in training proactive dialogue agents is scarce, despite fine-tuning and reinforcement learning . a recent study has shown that the effectiveness of supervised fine-touring is limited by the lack of high-quality, domain-specific training data.
Approach: They propose a framework for training recruitment proactive dialogue agents using a high-fidelity user simulator and a multi-dimensional evaluation framework based on Chain-of-Intention.
Outcome: The proposed framework outperforms existing simulator-based data selection strategies in a real-world recruitment scenario.
Do LLMs Know and Understand Domain Conceptual Knowledge? (2025.findings-emnlp)

Copied to clipboard

Challenge: Concept sememe tree is a hierarchical structure that represents lexical meaning by combining sememes and their relationships.
Approach: They introduce a Neighbor Semantic Structure (NSS) and a Chain-of-Thought prompting method to evaluate the effectiveness of various Large Language Models (LLMs) in generating concept sememe trees.
Outcome: The proposed method guides LLMs through an analysis of a term’s intrinsic core concepts, essential attributes, and semantic relationships, enabling the generation of concept sememe trees.
Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction (2024.findings-emnlp)

Copied to clipboard

Challenge: Experimental results show a significant performance gap between tuning-based approaches and event extraction approaches.
Approach: They propose a debate as optimization system where the primary objective is to iteratively refine the large language models outputs through debating without parameter tuning.
Outcome: The proposed system reduces performance gap between supervised approaches and tuning-free methods by 18.1% and 17.8% on ACE05 and 17.9% and 15.2% on CASIE respectively.
Annotate Chinese Aspect with UMR——a Case Study on the Liitle Prince (2024.lrec-main)

Copied to clipboard

Challenge: Uniform Meaning Representation (UMR) is a graphbased cross-linguistically applicable semantic representation that allows for deep semantic analysis.
Approach: They propose to use an aspectual lattice to adapt to different languages and design values that encompass both viewpoint aspect and situation aspect.
Outcome: The proposed representations are based on the Chinese version of The Little Prince and are compared with other representations.

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