25 papers
Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning
Junkai Chen, Yuhao He, Qianshan Wei +19
As multimodal large language models (MLLMs) become more capable and widely deployed, concerns about privacy and safety have become increasingly pressing. Machine unlearning offers…
Understanding Machine Unlearning Through the Lens of Mode Connectivity
Jiali Cheng, Hadi Amiri
Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch. Despite recent progress, the loss landscape and optimization geome…
Fair Cognitive Impairment Detection Through Unlearning
William Nguyen, Jiali Cheng, Hadi Amiri
Mild Cognitive Impairment (MCI) is a medical condition characterized by a noticeable decline in memory, language, or thinking abilities. MCI detection from spontaneous speech is pr…
TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation
Ziheng Chen, Jiali Cheng, Zezhong Fan +4
Generative recommendation formulates next-item prediction as autoregressive generation over semantic ID (SID) sequences derived from users' historical interactions, making modern r…
Fine-Grained Graph Generation through Latent Mixture Scheduling
Nidhi Vakil, Hadi Amiri
Structure aware graph generation aims to generate graphs that satisfy given topological properties. It has applications in domains such as drug discovery, social network modeling,…
CURE:Circuit-Aware Unlearning for LLM-based Recommendation
Ziheng Chen, Jiali Cheng, Zezhong Fan +4
Recent advances in large language models (LLMs) have opened new opportunities for recommender systems by enabling rich semantic understanding and reasoning about user interests and…
Investigating Tool-Memory Conflicts in Tool-Augmented LLMs
Jiali Cheng, Rui Pan, Hadi Amiri
Tool-augmented large language models (LLMs) have powered many applications. However, they are likely to suffer from knowledge conflict. In this paper, we propose a new type of know…
A Mechanistic Perspective and Circuit-Guided Difficulty Metric for Unlearning
Jiali Cheng, Ziheng Chen, Chirag Agarwal +1
Machine unlearning is becoming essential for building trustworthy and compliant language models. Yet unlearning success varies considerably across individual samples: some are reli…
Do Students Debias Like Teachers? On the Distillability of Bias Mitigation Methods
Jiali Cheng, Chirag Agarwal, Hadi Amiri
Knowledge distillation (KD) is an effective method for model compression and transferring knowledge between models. However, its effect on model's robustness against spurious corre…
WebATLAS: An LLM Agent with Experience-Driven Memory and Action Simulation
Jiali Cheng, Anjishnu Kumar, Roshan Lal +7
Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tu…
FUTURE: Flexible Unlearning for Tree Ensemble
Ziheng Chen, Jin Huang, Jiali Cheng +5
Tree ensembles are widely recognized for their effectiveness in classification tasks, achieving state-of-the-art performance across diverse domains, including bioinformatics, finan…
Speech Unlearning
Jiali Cheng, Hadi Amiri
We introduce machine unlearning for speech tasks, a novel and underexplored research problem that aims to efficiently and effectively remove the influence of specific data from tra…
Unveil Multi-Picture Descriptions for Multilingual Mild Cognitive Impairment Detection via Contrastive Learning
Kristin Qi, Jiali Cheng, Youxiang Zhu +2
Detecting Mild Cognitive Impairment from picture descriptions is critical yet challenging, especially in multilingual and multiple picture settings. Prior work has primarily focuse…
Understanding Machine Unlearning Through the Lens of Mode Connectivity
Jiali Cheng, Hadi Amiri
Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch. Despite recent progress, the loss landscape and optimization geome…
Linguistic Blind Spots of Large Language Models
Jiali Cheng, Hadi Amiri
Large language models (LLMs) are the foundation of many AI applications today. However, despite their remarkable proficiency in generating coherent text, questions linger regarding…
EqualizeIR: Mitigating Linguistic Biases in Retrieval Models
Jiali Cheng, Hadi Amiri
This study finds that existing information retrieval (IR) models show significant biases based on the linguistic complexity of input queries, performing well on linguistically simp…
FairFlow: Mitigating Dataset Biases through Undecided Learning
Jiali Cheng, Hadi Amiri
Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing fr…
FROG: Fair Removal on Graphs
Ziheng Chen, Jiali Cheng, Hadi Amiri +5
With growing emphasis on privacy regulations, machine unlearning has become increasingly critical in real-world applications such as social networks and recommender systems, many o…
Tool Unlearning for Tool-Augmented LLMs
Jiali Cheng, Hadi Amiri
Tool-augmented large language models (LLMs) are often trained on datasets of query-response pairs, which embed the ability to use tools or APIs directly into the parametric knowled…
LingGen: Scalable Multi-Attribute Linguistic Control via Power-Law Masking
Mohamed Elgaar, Hadi Amiri
We present LingGen, a controlled text generation model that allows fine-grained control over a large number of real-valued linguistic attributes. It encodes target attribute values…
MedDec: A Dataset for Extracting Medical Decisions from Discharge Summaries
Mohamed Elgaar, Jiali Cheng, Nidhi Vakil +2
Medical decisions directly impact individuals' health and well-being. Extracting decision spans from clinical notes plays a crucial role in understanding medical decision-making pr…
CogniVoice: Multimodal and Multilingual Fusion Networks for Mild Cognitive Impairment Assessment from Spontaneous Speech
Jiali Cheng, Mohamed Elgaar, Nidhi Vakil +1
Mild Cognitive Impairment (MCI) is a medical condition characterized by noticeable declines in memory and cognitive abilities, potentially affecting individual's daily activities.…
MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning
Jiali Cheng, Hadi Amiri
Recent advancements in Machine Unlearning (MU) have introduced solutions to selectively remove certain training samples, such as those with outdated or sensitive information, from…
Complexity-Guided Curriculum Learning for Text Graphs
Nidhi Vakil, Hadi Amiri
Curriculum learning provides a systematic approach to training. It refines training progressively, tailors training to task requirements, and improves generalization through exposu…