Papers by Jingjie Zeng

14 papers
Human-Inspired Obfuscation for Model Unlearning: Local and Global Strategies with Hyperbolic Representations (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for unlearning large language models struggle to balance effective forgetting with maintaining model utility.
Approach: They propose a human-inspired unlearning framework that simulates forgetting on fuzzy data and represents them in hyperbolic and Euclidean spaces.
Outcome: The proposed framework is able to forget sensitive content while maintaining the model’s language understanding, fluency, and benchmark performance.
Exploring the Capability of Multimodal LLMs with Yonkoma Manga: The YManga Dataset and Its Challenging Tasks (2024.findings-emnlp)

Copied to clipboard

Challenge: YManga dataset is the first specifically designed for yonkoma manga understanding .
Approach: They propose to use a dataset of 1,015 yonkoma strips with 10,150 human annotations to define three tasks for panel sequence detection, intent generation and description generation for masked panels.
Outcome: The proposed dataset contains 1,015 high-quality yonkoma strips with 10,150 human annotations.
Sarcasm-R1: Enhancing Sarcasm Detection through Focused Reasoning (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for sarcasm detection are limited by supervised learning or prompt engineering . a new approach decomposes sarcasm detection into three dimensions: language, context, and emotion .
Approach: They propose a method that decomposes sarcasm detection into three dimensions: language, context, and emotion.
Outcome: The proposed method outperforms state-of-the-art methods in most cases.
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.
To Judge or Not to Judge: Can Large Language Models Leverage the Dispute Focus in Legal Judgment? (2026.acl-long)

Copied to clipboard

Challenge: Existing research on large language models for legal judgment prediction fails to address the complexity of civil judicial cases.
Approach: They propose a framework that leverages the dispute focus to guide LLMs through a structured, judge-like cognitive workflow.
Outcome: The proposed framework can guide LLMs through a structured, judge-like cognitive workflow.
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.
PiKGL: Leveraging Pruned Knowledge Graphs for Explainable Stance Detection (2026.tacl-1)

Copied to clipboard

Challenge: Experimental results demonstrate that a Pruned interpretable knowledge Graph Learning framework for explainable stance detection is state-of-the-art for social media stance prediction.
Approach: They propose a Pruned interpretable knowledge Graph Learning framework for explainable stance detection that incorporates commonsense knowledge and prunes redundant information to ensure precision and minimize noise.
Outcome: The proposed framework achieves state-of-the-art on three public datasets.
GLA: Grounding Large Language Models in Molecular Hierarchy for Chemical Understanding (2026.findings-acl)

Copied to clipboard

Challenge: Existing molecule-language models obscure the hierarchical organization of chemical semantics . Existing models rely on linear or uniform encodings, causing structural distortion .
Approach: They propose a framework that integrates intrinsic molecular topology into large language models.
Outcome: The proposed framework improves on cross-modal retrieval, captioning, and property prediction benchmarks.
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.
Targeted Distillation for Sentiment Analysis (2025.emnlp-main)

Copied to clipboard

Challenge: Recent studies demonstrate that large language models exhibit remarkable capabilities and achieve state-of-the-art performance in diverse sentiment analysis tasks.
Approach: They propose a distillation framework that decouples knowledge from alignment and introduces a sentiment analysis benchmark that covers a diverse set of tasks.
Outcome: The proposed framework improves models' generalization to unseen tasks and their generalization is strong against existing small-scale models.
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.
LOTUS: Evolving Multimodal Unlearning via Hyperbolic Entailment and Lorentz Transport (2026.acl-long)

Copied to clipboard

Challenge: Existing unlearning methods suffer from a geometric mismatch, causing catastrophic forgetting or unsafe substitution.
Approach: They propose a framework for surgical semantic pruning within the Lorentz manifold.
Outcome: Experiments on MLLMU-Bench show that LOTUS significantly outperforms baselines while maintaining general utility.
Label-Enhanced Hierarchical Contextualized Representation for Sequential Metaphor Identification (2021.emnlp-main)

Copied to clipboard

Challenge: Recent approaches to identify metaphors ignore extra information from data, such as contextual information and broader discourse information.
Approach: They propose a model augmented with hierarchical contextualized representation to extract more information from both sentence-level and discourse-level.
Outcome: The proposed model outperforms state-of-the-art methods on two tasks using a VUA dataset.

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