Papers by Xiaomeng Jin

9 papers
LUME: LLM Unlearning with Multitask Evaluations (2025.findings-emnlp)

Copied to clipboard

Challenge: Unlearning aims to remove copyrighted, sensitive, or private content from large language models without a full retraining.
Approach: They propose a multi-task unlearning benchmark LUME that unlearns short novels, biographies and public biographie .
Outcome: The proposed benchmark unlearns short novels, biographies and public biographie . it also releases fine-tuned models with 1B and 7B parameter sizes as targets .
SYNTHIA: Novel Concept Design with Affordance Composition (2025.acl-long)

Copied to clipboard

Challenge: Existing studies on concept design using text-to-image models have enabled rapid ideation of novel visual concepts.
Approach: They propose a framework for generating novel, functionally coherent designs based on desired affordances by decomposing concepts into parts and affordance . they also develop a curriculum learning scheme that fine-tunes T2I models to progressively learn affordance composition while maintaining visual novelty.
Outcome: The proposed framework outperforms state-of-the-art models for novelty and functional coherence in human evaluation.
Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods to remove unwanted knowledge from large language models are formulated as minimizing memorization through the loss of the model.
Approach: They propose a normalized gradient difference algorithm that optimizes a forgetting objective and an automatic learning rate scheduler that allows for better control over the trade-off between the objectives.
Outcome: The proposed method improves on TOFU and MUSE datasets while exhibiting stable training.
Event Schema Induction with Double Graph Autoencoders (2022.naacl-main)

Copied to clipboard

Challenge: Experimental results show that a new method for learning event schemas from historical events is effective.
Approach: They propose a new event schema induction framework which captures global dependencies among nodes in event graphs.
Outcome: Experimental results show that the proposed model can learn event schemas with global consistency.
Adversarial Robustness for Large Language NER models using Disentanglement and Word Attributions (2023.findings-emnlp)

Copied to clipboard

Challenge: Named Entity Recognition (NER) tasks are becoming more challenging due to the introduction of complex tagsets, which often leads to the failure of existing NER systems in accurately recognizing these entities.
Approach: They propose a novel attack which relies on disentanglement and word attribution techniques to learn an embedding and identifying important words across both components.
Outcome: The proposed approach improves the F1 score over the original LLM model by 8% and 18% on CoNLL-2003 and Ontonotes 5.0 datasets respectively.
Schema-based Data Augmentation for Event Extraction (2024.lrec-main)

Copied to clipboard

Challenge: Existing data augmentation methods rely on language models to train event extraction models.
Approach: They propose a schema-based data augmentation method that utilizes event schemas to guide the data generation process.
Outcome: The proposed method produces high-quality generated data and significantly improves model performance.
Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) allow repeatable experiments in which individual characteristics can be precisely defined.
Approach: They propose a scalable experimental paradigm using Large Language Models to simulate multi-stage supply chain dynamics.
Outcome: The proposed model systematically replicates and validates the results of a behavioral simulation on agents in multi-stage supply chain dynamics.

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