Papers by Yuanyuan Liang

10 papers
ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection (2026.findings-acl)

Copied to clipboard

Challenge: Existing toxic content detection methods focus on sentence-level classification but fail to provide readable and contiguous toxic evidence spans.
Approach: They propose an explainability-oriented method for Chinese toxic content detection methods . they refine saliency cues into fine-grained toxic spans with lightweight LLM guidance .
Outcome: The proposed method improves classification accuracy and toxic span extraction while preserving efficient encoder-based inference and producing more coherent explanations.
It’s Not Bragging If You Can Back It Up: Can LLMs Understand Braggings? (2025.acl-long)

Copied to clipboard

Challenge: Bragging is a pervasive social-linguistic phenomenon that reflects complex human interaction patterns.
Approach: They propose to use bragging recognition, bragging explanation, and bragging generation tasks to examine bragging in large language models (LLMs) .
Outcome: The proposed models can identify bragging intent, social appropriateness, and account for context sensitivity and provide new insights into how LLMs process bragging.
Retrieval Augmented Instruction Tuning for Open NER with Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Existing studies have focused on integrating large language models (LLMs) with information extraction (IE) however, the best approach to incorporate information with LLMs for IE remains an open question.
Approach: They propose to use a Chinese IT dataset to perform RA-IT for IE . they use semantically similar examples from the training dataset as the context .
Outcome: The proposed approach is evaluated in English and Chinese scenarios.
CogEvolve: A Multimodal Benchmark for Evaluating Relational Reasoning in Semantic Extension (2026.acl-long)

Copied to clipboard

Challenge: a gap exists between human embodied logic and machine statistical learning . authors: models internalize statistical patterns or mimic static recognition .
Approach: They propose a cognitive linguistic benchmark to test whether large language models internalize statistical logic or not . they find that models function as "Super-Associators" expert at static recognition yet fail at causal reasoning .
Outcome: The proposed model fails at causal reasoning and has a high-fidelity concept representation but lacks transformational operators essential for true relational understanding.
STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on Chinese hate speech detection lack span-level fine-grained annotations.
Approach: They construct a Span-level target-aware Toxicity Extraction dataset and evaluate existing models for Chinese hateful slang.
Outcome: The proposed dataset is the first span-level Chinese hate speech dataset and evaluates the ability of existing models to understand hate semantics.
COCOGEC: Counterfactual Generation for Robust Grammatical Error Correction (2026.findings-acl)

Copied to clipboard

Challenge: Existing GEC models fail to understand error patterns in varying contexts . a framework that generates copies of training instances with error-irrelevant contexts altered is proposed .
Approach: They propose a framework that generates copies of training instances with error-irrelevant contexts altered.
Outcome: The proposed framework outperforms baselines on the simulated tasks and outperformed existing models.
Mechanistic Insights into Deferred Semantic Drift in LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) face a fundamental challenge with delayed disambiguation: how can a model update the meaning of an early, ambiguous token when clarifying context only appears later in the sequence?
Approach: They propose a method to defer semantic re-evaluation to subsequent tokens in a process they call "Deferred Semantic Drift" they demonstrate this mechanism in metaphor comprehension and provide causal validation by steering model outputs towards literal or metaphorical meanings via targeted activation interventions.
Outcome: The proposed model can update the meaning of an ambiguous word when clarifying context arrives only after it has been processed.
Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for question generation over knowledge bases rely on annotated data for fine-tuning . emergence of Large Language Models (LLMs) has shown impressive generalization ability in few-shot tasks.
Approach: They propose to use a logical form to generate a question in a reasoning problem . they propose to extend the prompting method into a method that can generate questions in logical forms .
Outcome: The proposed method outperforms baselines on three public KBQG datasets.
Sheep’s Skin, Wolf’s Deeds: Are LLMs Ready for Metaphorical Implicit Hate Speech? (2025.acl-long)

Copied to clipboard

Challenge: specialized models fail to detect implicit hate speech due to its indirectly expressed hateful intent . advanced LLMs often misinterpret metaphorical implicit hate content, resulting in its propagation .
Approach: They propose a Jailbreaking strategy and Energy-based Constrained Decoding techniques to detect implicit hate speech in large language models.
Outcome: The proposed model can generate metaphorical implicit hate speech, but it fails to detect it effectively.

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