Search Results for author:
Found 14 papers, 4 papers with code
Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In
Following the advancement of large language models (LLMs), the development of LLM-based autonomous agents has become increasingly prevalent.
Exploring Straightforward Conversational Red-Teaming
Large language models (LLMs) are increasingly used in business dialogue systems but they pose security and ethical risks.
Can You Trust Your Metric? Automatic Concatenation-Based Tests for Metric Validity
We applied these tests in a model safety scenario to assess the reliability of harmfulness detection metrics, uncovering a number of inconsistencies.
From Zero to Hero: Cold-Start Anomaly Detection
This paper studies the realistic but underexplored cold-start setting where an anomaly detection model is initialized using zero-shot guidance, but subsequently receives a small number of contaminated observations (namely, that may include anomalies).
Ranked #1 on
Cold-Start Anomaly Detection
on BANKING77-OOS
Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations.
Unveiling Safety Vulnerabilities of Large Language Models
As large language models become more prevalent, their possible harmful or inappropriate responses are a cause for concern.
Characterizing how 'distributional' NLP corpora distance metrics are
We quantify this quality by constructing a Known-Similarity Corpora set from two paraphrase corpora and calculating the distance between paired corpora from it.
Measuring the Measuring Tools: An Automatic Evaluation of Semantic Metrics for Text Corpora
The ability to compare the semantic similarity between text corpora is important in a variety of natural language processing applications.
Understanding the Properties of Generated Corpora
Models for text generation have become focal for many research tasks and especially for the generation of sentence corpora.
Classifier Data Quality: A Geometric Complexity Based Method for Automated Baseline And Insights Generation
Testing Machine Learning (ML) models and AI-Infused Applications (AIIAs), or systems that contain ML models, is highly challenging.
Balancing via Generation for Multi-Class Text Classification Improvement
Data balancing is a known technique for improving the performance of classification tasks.
Not Enough Data? Deep Learning to the Rescue!
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.
Neural network gradient-based learning of black-box function interfaces
We propose a method for end-to-end training of a base neural network that integrates calls to existing black-box functions.
Estimate and Replace: A Novel Approach to Integrating Deep Neural Networks with Existing Applications
At inference time, we replace each estimator with its existing application counterpart and let the base network solve the task by interacting with the existing application.
