Narine Kokhlikyan — accepted AI-conference papers

2026

CIMemories: A Compositional Benchmark For Contextual Integrity In LLMs

Niloofar Mireshghallah, Neal Mangaokar, Narine Kokhlikyan, Arman Zharmagambetov, Manzil Zaheer, Saeed Mahloujifar +1

ICLR 2026poster

Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory creates critical risks when sensitive information is revealed in inappropriate contexts. We present CIMemories, a benchmark for evaluating whet…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Hallucination Reduction with CASAL: Contrastive Activation Steering for Amortized Learning

Wannan Yang, Xinchi Qiu, Lei Yu, Yuchen Zhang, Aobo Yang, Narine Kokhlikyan +2

ICLR 2026poster

Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown that models encode linear representations of their own knowledge and that activation steering can reduce hallucinations. Th…

Cited by 0 Source ↗Scholar ↗

2026

How much can language models memorize?

John Morris, Chawin Sitawarin, Narine Kokhlikyan, Chuan Guo, Edward Suh, Alexander Rush +2

ICML 2026oral

We propose a new method for estimating how much a model knows about a datapoint and use it to measure the capacity of modern language models. Prior studies of language model memorization have struggled to disentangle memorization from generalization. We formally separate memorization into two compon…

Cited by 0 Source ↗Scholar ↗

2024

Measuring Dejavu Memorization Efficiently

Narine Kokhlikyan, Bargav Jayaraman, Florian Bordes, Chuan Guo, Kamalika Chaudhuri

NeurIPS 2024poster

Recent research has shown that representation learning models may accidentally memorize their training data. For example, the déjà vu method shows that for certain representation learning models and training images, it is sometimes possible to correctly predict the foreground label given only the re…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2023

Error Discovery By Clustering Influence Embeddings

Fulton Wang, Julius Adebayo, Sarah Tan, Diego Garcia-Olano, Narine Kokhlikyan

NeurIPS 2023poster

We present a method for identifying groups of test examples---slices---on which a model under-performs, a task now known as slice discovery. We formalize coherence---a requirement that erroneous predictions, within a slice, should be wrong for the same reason---as a key property that any slice disco…

Cited by 4 Source ↗PDF ↗Scholar ↗

2023

Mind the Pool: Convolutional Neural Networks Can Overfit Input Size

Bilal Alsallakh, David Yan, Narine Kokhlikyan, Vivek Miglani, Orion Reblitz-Richardson, Pamela Bhattacharya

ICLR 2023poster

We demonstrate how convolutional neural networks can overfit the input size: The accuracy drops significantly when using certain sizes, compared with favorable ones. This issue is inherent to pooling arithmetic, with standard downsampling layers playing a major role in favoring certain input sizes a…

Cited by 4 Source ↗PDF ↗Scholar ↗

2021

Mind the Pad -- CNNs Can Develop Blind Spots

Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani, Jun Yuan, Orion Reblitz-Richardson

ICLR 2021spotlight

We show how feature maps in convolutional networks are susceptible to spatial bias. Due to a combination of architectural choices, the activation at certain locations is systematically elevated or weakened. The major source of this bias is the padding mechanism. Depending on several aspects of convo…

Cited by 107 Source ↗PDF ↗Scholar ↗