47 citations · 145 across the 24 of their papers we have counts for
27 papers
ACON: Optimizing Context Compression for Long-horizon LLM Agents
Minki Kang, Wei-Ning Chen, Dongge Han +5
Large language models (LLMs) are increasingly deployed as agents in dynamic real-world environments, where success depends on maintaining precise records of actions and observation…
Learning GUI Grounding with Spatial Reasoning from Visual Feedback
Yu Zhao, Wei-Ning Chen, Huseyin Atahan Inan +8
Graphical User Interface (GUI) grounding is commonly framed as a coordinate prediction task -- given a natural language instruction, generate on-screen coordinates for actions such…
Contextual Integrity in LLMs via Reasoning and Reinforcement Learning
Guangchen Lan, Huseyin A. Inan, Sahar Abdelnabi +5
As the era of autonomous agents making decisions on behalf of users unfolds, ensuring contextual integrity (CI) -- what is the appropriate information to share while carrying out a…
On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
Guanghao Ye, Khiem Duc Pham, Xinzhi Zhang +5
Recent AI advancements, such as OpenAI's new models, are transforming LLMs into LRMs (Large Reasoning Models) that perform reasoning during inference, taking extra time and compute…
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs +9
Text data has become extremely valuable due to the emergence of machine learning algorithms that learn from it. A lot of high-quality text data generated in the real world is priva…
Differentially Private Training of Mixture of Experts Models
Pierre Tholoniat, Huseyin A. Inan, Janardhan Kulkarni +1
This position paper investigates the integration of Differential Privacy (DP) in the training of Mixture of Experts (MoE) models within the field of natural language processing. As…
Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks
Ruixiang Tang, Gord Lueck, Rodolfo Quispe +3
Large language models have revolutionized the field of NLP by achieving state-of-the-art performance on various tasks. However, there is a concern that these models may disclose in…
Privately Aligning Language Models with Reinforcement Learning
Fan Wu, Huseyin A. Inan, Arturs Backurs +3
Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training ins…
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Xinyu Tang, Richard Shin, Huseyin A. Inan +6
We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the priv…
Planting and Mitigating Memorized Content in Predictive-Text Language Models
C. M. Downey, Wei Dai, Huseyin A. Inan +3
Language models are widely deployed to provide automatic text completion services in user products. However, recent research has revealed that language models (especially large one…
Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe
Xiang Yue, Huseyin A. Inan, Xuechen Li +6
Privacy concerns have attracted increasing attention in data-driven products due to the tendency of machine learning models to memorize sensitive training data. Generating syntheti…
Combing for Credentials: Active Pattern Extraction from Smart Reply
Bargav Jayaraman, Esha Ghosh, Melissa Chase +3
Pre-trained large language models, such as GPT\nobreakdash-2 and BERT, are often fine-tuned to achieve state-of-the-art performance on a downstream task. One natural example is the…
When Does Differentially Private Learning Not Suffer in High Dimensions?
Xuechen Li, Daogao Liu, Tatsunori Hashimoto +4
Large pretrained models can be privately fine-tuned to achieve performance approaching that of non-private models. A common theme in these results is the surprising observation tha…
Privacy Leakage in Text Classification: A Data Extraction Approach
Adel Elmahdy, Huseyin A. Inan, Robert Sim
Recent work has demonstrated the successful extraction of training data from generative language models. However, it is not evident whether such extraction is feasible in text clas…
Differentially Private Model Compression
Fatemehsadat Mireshghallah, Arturs Backurs, Huseyin A Inan +2
Recent papers have shown that large pre-trained language models (LLMs) such as BERT, GPT-2 can be fine-tuned on private data to achieve performance comparable to non-private models…
Differentially Private Fine-tuning of Language Models
Da Yu, Saurabh Naik, Arturs Backurs +9
We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus…
Membership Inference on Word Embedding and Beyond
Saeed Mahloujifar, Huseyin A. Inan, Melissa Chase +2
In the text processing context, most ML models are built on word embeddings. These embeddings are themselves trained on some datasets, potentially containing sensitive data. In som…
On Privacy and Confidentiality of Communications in Organizational Graphs
Masoumeh Shafieinejad, Huseyin Inan, Marcello Hasegawa +1
Machine learned models trained on organizational communication data, such as emails in an enterprise, carry unique risks of breaching confidentiality, even if the model is intended…
Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
Fatemehsadat Mireshghallah, Huseyin A. Inan, Marcello Hasegawa +3
Neural language models are known to have a high capacity for memorization of training samples. This may have serious privacy implications when training models on user content such…
Training Data Leakage Analysis in Language Models
Huseyin A. Inan, Osman Ramadan, Lukas Wutschitz +4
Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated t…
rTop-k: A Statistical Estimation Approach to Distributed SGD
Leighton Pate Barnes, Huseyin A. Inan, Berivan Isik +1
The large communication cost for exchanging gradients between different nodes significantly limits the scalability of distributed training for large-scale learning models. Motivate…
Improving Semantic Parsing with Neural Generator-Reranker Architecture
Huseyin A. Inan, Gaurav Singh Tomar, Huapu Pan
Semantic parsing is the problem of deriving machine interpretable meaning representations from natural language utterances. Neural models with encoder-decoder architectures have re…
On the Optimality of the Kautz-Singleton Construction in Probabilistic Group Testing
Huseyin A. Inan, Peter Kairouz, Mary Wootters +1
We consider the probabilistic group testing problem where random defective items in a large population of items are identified with high probability by applying binary test…
Sparse Combinatorial Group Testing
Huseyin A. Inan, Peter Kairouz, Ayfer Ozgur
In combinatorial group testing (CGT), the objective is to identify the set of at most defective items from a pool of items using as few tests as possible. The celebrated re…