Papers by Ateret Anaby Tavor
From Zero to Hero: Cold-Start Anomaly Detection (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing anomaly detection methods require previous observations to be effective . contaminated observations are often not observed, making them ineffective . |
| Approach: | They propose a method that adapts a zero-shot anomaly detector to contaminated observations . they propose an evaluation suite consisting of evaluation protocols and metrics . |
| Outcome: | The proposed method adapts the zero-shot anomaly detector to contaminated observations. |
Reliable and Interpretable Drift Detection in Streams of Short Texts (2023.acl-industry)
Copied to clipboard
| Challenge: | Data drift is a key factor leading to model performance degradation over time. |
| Approach: | They propose a framework for reliable model-agnostic change-point detection and interpretation in large task-oriented dialog systems. |
| Outcome: | The proposed framework is effective in multiple customer deployments. |
Gaining Insights into Unrecognized User Utterances in Task-Oriented Dialog Systems (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Goal-oriented dialog systems fail to recognize the intent of natural language requests due to system errors, incomplete service coverage, or insufficient training. |
| Approach: | They propose an end-to-end pipeline for processing unrecognized user utterances, deployed in a commercial task-oriented dialog system, including a specifically-tailored clustering algorithm, a novel approach to cluster representative extraction, and cluster naming. |
| Outcome: | The proposed components show that they improve the performance of the proposed system in the analysis of unrecognized user requests. |
Generating OpenAPI Specifications from Online API Documentation with Large Language Models (2025.acl-industry)
Copied to clipboard
Koren Lazar, Matan Vetzler, Kiran Kate, Jason Tsay, David Boaz, Himanshu Gupta, Avraham Shinnar, Rohith D Vallam, David Amid, Esther Goldbraich, Jim Laredo, Ateret Anaby Tavor
| Challenge: | API specifications are often presented as unstructured HTML pages, requiring external users to manually convert it into a structured format. |
| Approach: | They propose a framework that transforms long API documentation pages into consistent, machine-readable API specifications. |
| Outcome: | The proposed framework generalizes well across hundreds of APIs and produces valid OpenAPI specifications that encapsulate most of the information from the original documentation. |
Balancing via Generation for Multi-Class Text Classification Improvement (2020.findings-emnlp)
Copied to clipboard
| Challenge: | balancing is a known technique for improving classification performance . balancy is based on a balancing policy and a text generation mechanism . |
| Approach: | They propose a balancing-via-generation framework that augments a dataset for more balanced distribution by using a text generation mechanism. |
| Outcome: | The proposed framework can augment a dataset for more balanced distribution while under-sampling others. |
Towards Enforcing Company Policy Adherence in Agentic Workflows (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) agents are transforming business processes with minimal human oversight. |
| Approach: | They propose a deterministic, transparent, and modular framework for enforcing business policy adherence in agentic workflows. |
| Outcome: | The proposed framework shows encouraging preliminary results in policy enforcement on the -bench Airlines domain. |
Exploring Straightforward Methods for Automatic Conversational Red-Teaming (2025.naacl-industry)
Copied to clipboard
George Kour, Naama Zwerdling, Marcel Zalmanovici, Ateret Anaby Tavor, Ora Nova Fandina, Eitan Farchi
| Challenge: | Large language models (LLMs) are increasingly used in business dialogue systems but they also pose security and ethical risks. |
| Approach: | They propose to use off-the-shelf large language models to create red-team attacks by eliciting undesired outputs from an attacker LLM. |
| Outcome: | The proposed models can adapt their attack strategies based on prior attempts, but their effectiveness decreases as the alignment of the target model improves. |
Text Augmentation Using Dataset Reconstruction for Low-Resource Classification (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for text classification use labeled data, but labeles are expensive and difficult to obtain. |
| Approach: | They propose a novel method of data augmentation using the text-generation capabilities of language models. |
| Outcome: | The proposed method improves the current state-of-the-art methods for data augmentation on multi-class datasets. |
A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Using large language models, we evaluated their robustness on multiple datasets. |
| Approach: | They propose a new metric for assessing model robustness by empirical evaluation of several models on multiple datasets. |
| Outcome: | The proposed metric is based on a set of datasets that are constructed by introducing naturally-occurring, non-malicious perturbations or by generating semantically equivalent paraphrases of input questions or statements. |
Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In (2025.findings-naacl)
Copied to clipboard
| Challenge: | Indirect prompt injection attacks, prompted by harmless and unrelated requests, can significantly increase the likelihood of the agent performing subsequent malicious actions. |
| Approach: | They propose to implement a simple reflection mechanism that prompts the agent to reassess the safety of its actions during execution, which can help mitigate this vulnerability. |
| Outcome: | The proposed method reduces the success of such attacks by prompting the agent to reassess its actions during execution. |
We’ve had this conversation before: A Novel Approach to Measuring Dialog Similarity (2021.emnlp-main)
Copied to clipboard
| Challenge: | Dialogs are a building block of human natural language interactions. |
| Approach: | They propose a new edit distance metric for dialog similarity analysis using conversation semantics, conversation flow, and the participants. |
| Outcome: | The proposed method outperforms existing methods on two publicly available datasets and is better aligned with human perception of conversation similarity. |
Effective Red-Teaming of Policy-Adherent Agents (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Model (LLM)-based agents are increasingly used in domains with strict policies, such as refund eligibility or cancellation rules. |
| Approach: | They propose a multi-agent red-teaming system that leverages policy-aware persuasive strategies to undermine a policy-adherence agent in a customer-service scenario. |
| Outcome: | The proposed model outperforms jailbreak methods and tau-break to assess agent's robustness against manipulative user behavior. |
Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models (2025.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models exhibit subjective preferences, opinions, and beliefs, which may shape their behavior, influence advice and recommendations, and potentially reinforce certain viewpoints. |
| Approach: | They developed a benchmark to assess LLMs’ subjective inclinations across societal, cultural, ethical, and personal domains. |
| Outcome: | The proposed benchmark assesses LLMs’ subjective inclinations across societal, cultural, ethical, and personal domains. |