32 citations · 66 across the 17 of their papers we have counts for
17 papers
Efficient Agent Evaluation via Diversity-Guided User Simulation
Itay Nakash, George Kour, Ateret Anaby-Tavor
Large language models (LLMs) are increasingly deployed as customer-facing agents, yet evaluating their reliability remains challenging due to stochastic, multi-turn interactions. C…
Effective Red-Teaming of Policy-Adherent Agents
Itay Nakash, George Kour, Koren Lazar +3
Task-oriented LLM-based agents are increasingly used in domains with strict policies, such as refund eligibility or cancellation rules. The challenge lies in ensuring that the agen…
Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models
George Kour, Itay Nakash, Ateret Anaby-Tavor +1
As Large Language Models (LLMs) become deeply integrated into human life and increasingly influence decision-making, it's crucial to evaluate whether and to what extent they exhibi…
Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In
Itay Nakash, George Kour, Guy Uziel +1
Following the advancement of large language models (LLMs), the development of LLM-based autonomous agents has become increasingly prevalent. As a result, the need to understand the…
Exploring Straightforward Conversational Red-Teaming
George Kour, Naama Zwerdling, Marcel Zalmanovici +3
Large language models (LLMs) are increasingly used in business dialogue systems but they pose security and ethical risks. Multi-turn conversations, where context influences the mod…
How Safe is Your Safety Metric? Automatic Concatenation Tests for Metric Reliability
Ora Nova Fandina, Leshem Choshen, Eitan Farchi +3
Consider a scenario where a harmfulness evaluation metric intended to filter unsafe responses from a Large Language Model. When applied to individual harmful prompt-response pairs,…
From Zero to Hero: Cold-Start Anomaly Detection
Tal Reiss, George Kour, Naama Zwerdling +2
When first deploying an anomaly detection system, e.g., to detect out-of-scope queries in chatbots, there are no observed data, making data-driven approaches ineffective. Zero-shot…
Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor +35
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (trai…
Unveiling Safety Vulnerabilities of Large Language Models
George Kour, Marcel Zalmanovici, Naama Zwerdling +5
As large language models become more prevalent, their possible harmful or inappropriate responses are a cause for concern. This paper introduces a unique dataset containing adversa…
Characterizing how 'distributional' NLP corpora distance metrics are
Samuel Ackerman, George Kour, Eitan Farchi
A corpus of vector-embedded text documents has some empirical distribution. Given two corpora, we want to calculate a single metric of distance (e.g., Mauve, Frechet Inception) bet…
Measuring the Measuring Tools: An Automatic Evaluation of Semantic Metrics for Text Corpora
George Kour, Samuel Ackerman, Orna Raz +3
The ability to compare the semantic similarity between text corpora is important in a variety of natural language processing applications. However, standard methods for evaluating…
Understanding the Properties of Generated Corpora
Naama Zwerdling, Segev Shlomov, Esther Goldbraich +6
Models for text generation have become focal for many research tasks and especially for the generation of sentence corpora. However, understanding the properties of an automaticall…
High-quality Conversational Systems
Samuel Ackerman, Ateret Anaby-Tavor, Eitan Farchi +7
Conversational systems or chatbots are an example of AI-Infused Applications (AIIA). Chatbots are especially important as they are often the first interaction of clients with a bus…
Classifier Data Quality: A Geometric Complexity Based Method for Automated Baseline And Insights Generation
George Kour, Marcel Zalmanovici, Orna Raz +2
Testing Machine Learning (ML) models and AI-Infused Applications (AIIAs), or systems that contain ML models, is highly challenging. In addition to the challenges of testing classic…
Not Enough Data? Deep Learning to the Rescue!
Ateret Anaby-Tavor, Boaz Carmeli, Esther Goldbraich +5
Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a…
Neural network gradient-based learning of black-box function interfaces
Alon Jacovi, Guy Hadash, Einat Kermany +4
Deep neural networks work well at approximating complicated functions when provided with data and trained by gradient descent methods. At the same time, there is a vast amount of e…
Estimate and Replace: A Novel Approach to Integrating Deep Neural Networks with Existing Applications
Guy Hadash, Einat Kermany, Boaz Carmeli +3
Existing applications include a huge amount of knowledge that is out of reach for deep neural networks. This paper presents a novel approach for integrating calls to existing appli…