92 citations · 121 across the 25 of their papers we have counts for
25 papers
Learning User Simulators with Turing Rewards
Yingshan Susan Wang, Cedegao E. Zhang, Linlu Qiu +5
Learning to simulate human users in interactive settings could advance the training of agent assistants, evaluation of personalization systems, research in the social sciences, and…
Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing
Minglai Yang, Xinyan Velocity Yu, Pengyuan Li +22
Document parsing and recognition are fundamental capabilities for vision-language models (VLMs) and document processing systems. However, existing Optical Character Recognition (OC…
MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
Zexue He, Yu Wang, Churan Zhi +11
Existing evaluations of agents with memory typically assess memorization and action in isolation. One class of benchmarks evaluates memorization by testing recall of past conversat…
BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
Xin Xu, Xunzhi He, Churan Zhi +3
Existing studies on bias mitigation methods for large language models (LLMs) use diverse baselines and metrics to evaluate debiasing performance, leading to inconsistent comparison…
M+: Extending MemoryLLM with Scalable Long-Term Memory
Yu Wang, Dmitry Krotov, Yuanzhe Hu +6
Equipping large language models (LLMs) with latent-space memory has attracted increasing attention as they can extend the context window of existing language models. However, retai…
Towards LifeSpan Cognitive Systems
Yu Wang, Chi Han, Tongtong Wu +9
Building a human-like system that continuously interacts with complex environments -- whether simulated digital worlds or human society -- presents several key challenges. Central…
Large Scale Knowledge Washing
Yu Wang, Ruihan Wu, Zexue He +2
Large language models show impressive abilities in memorizing world knowledge, which leads to concerns regarding memorization of private information, toxic or sensitive knowledge,…
Cognitive Bias in Decision-Making with LLMs
Jessica Echterhoff, Yao Liu, Abeer Alessa +2
Large language models (LLMs) offer significant potential as tools to support an expanding range of decision-making tasks. Given their training on human (created) data, LLMs have be…
CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory
Zexue He, Leonid Karlinsky, Donghyun Kim +3
Large Language Models (LLMs) struggle to handle long input sequences due to high memory and runtime costs. Memory-augmented models have emerged as a promising solution to this prob…
LVCHAT: Facilitating Long Video Comprehension
Yu Wang, Zeyuan Zhang, Julian McAuley +1
Enabling large language models (LLMs) to read videos is vital for multimodal LLMs. Existing works show promise on short videos whereas long video (longer than e.g.~1 minute) compre…
InfoRank: Unbiased Learning-to-Rank via Conditional Mutual Information Minimization
Jiarui Jin, Zexue He, Mengyue Yang +4
Ranking items regarding individual user interests is a core technique of multiple downstream tasks such as recommender systems. Learning such a personalized ranker typically relies…
Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation
Yu Wang, Zexue He, Zhankui He +2
Understanding and accurately explaining compatibility relationships between fashion items is a challenging problem in the burgeoning domain of AI-driven outfit recommendations. Pre…
MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation
Zexue He, Yu Wang, An Yan +5
Curated datasets for healthcare are often limited due to the need of human annotations from experts. In this paper, we present MedEval, a multi-level, multi-task, and multi-domain…
Farzi Data: Autoregressive Data Distillation
Noveen Sachdeva, Zexue He, Wang-Cheng Kang +3
We study data distillation for auto-regressive machine learning tasks, where the input and output have a strict left-to-right causal structure. More specifically, we propose Farzi,…
Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models
An Yan, Yu Wang, Yiwu Zhong +8
Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients. However, two challe…
Learning Concise and Descriptive Attributes for Visual Recognition
An Yan, Yu Wang, Yiwu Zhong +6
Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attribute…
Targeted Data Generation: Finding and Fixing Model Weaknesses
Zexue He, Marco Tulio Ribeiro, Fereshte Khani
Even when aggregate accuracy is high, state-of-the-art NLP models often fail systematically on specific subgroups of data, resulting in unfair outcomes and eroding user trust. Addi…
"Nothing Abnormal": Disambiguating Medical Reports via Contrastive Knowledge Infusion
Zexue He, An Yan, Amilcare Gentili +2
Sharing medical reports is essential for patient-centered care. A recent line of work has focused on automatically generating reports with NLP methods. However, different audiences…
Synthetic Pre-Training Tasks for Neural Machine Translation
Zexue He, Graeme Blackwood, Rameswar Panda +2
Pre-training models with large crawled corpora can lead to issues such as toxicity and bias, as well as copyright and privacy concerns. A promising way of alleviating such concerns…
Controlling Bias Exposure for Fair Interpretable Predictions
Zexue He, Yu Wang, Julian McAuley +1
Recent work on reducing bias in NLP models usually focuses on protecting or isolating information related to a sensitive attribute (like gender or race). However, when sensitive in…
InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions
Bodhisattwa Prasad Majumder, Zexue He, Julian McAuley
Debiasing methods in NLP models traditionally focus on isolating information related to a sensitive attribute (e.g., gender or race). We instead argue that a favorable debiasing me…
Leashing the Inner Demons: Self-Detoxification for Language Models
Canwen Xu, Zexue He, Zhankui He +1
Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application. In this paper, we conduct extensive experim…
Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation
An Yan, Zexue He, Xing Lu +5
Radiology report generation aims at generating descriptive text from radiology images automatically, which may present an opportunity to improve radiology reporting and interpretat…
Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding
Zexue He, Bodhisattwa Prasad Majumder, Julian McAuley
Written language carries explicit and implicit biases that can distract from meaningful signals. For example, letters of reference may describe male and female candidates different…