Papers by Ahmed Salem
Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have increased the vulnerability of LLMs, but they can cause more severe damage than standalone systems if compromised. |
| Approach: | They propose a new type of attack that induces malfunctions by misleading the agent into executing repetitive or irrelevant actions. |
| Outcome: | The proposed attacks induce failure rates exceeding 80% in multiple scenarios, highlighting the substantial risks associated with this vulnerability. |
QSTN: A Modular Framework for Robust Questionnaire Inference with Large Language Models (2026.eacl-demo)
Copied to clipboard
| Challenge: | Questionnaire-like prompts have become an important format to probe, assess, and utilize large language models (LLMs) |
| Approach: | They propose an open-source Python framework for generating responses from questionnaire-style prompts to support in-silico surveys and annotation tasks with large language models (LLMs). |
| Outcome: | The proposed framework can be used to generate responses from questionnaire-style prompts and to perform annotations on large language models. |
SAHM: A Benchmark for Arabic Financial and Shari’ah-Compliant Reasoning (2026.acl-long)
Copied to clipboard
Rania Elbadry, Sarfraz Ahmad, Ahmed Heakl, Dani Bouch, Momina Ahsan, Muhra AlMahri, Marwa Elsaid Khalil, Yuxia Wang, Salem Lahlou, Sophia Ananiadou, Veselin Stoyanov, Jimin Huang, Xueqing Peng, Preslav Nakov, Zhuohan Xie
| Challenge: | English financial NLP has progressed rapidly through benchmarks for sentiment, document understanding, and financial question answering. |
| Approach: | They propose a document-grounded benchmark and instruction-tuning dataset for Arabic financial NLP and Shari’ah-compliant reasoning. |
| Outcome: | The proposed dataset contains 14,380 expert-verified instances spanning seven tasks . it includes financial sentiment analysis, extractive summarization, and event–cause reasoning . |
ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are rapidly transitioning from passive text generators to autonomous agents that act and communicate on behalf of users. |
| Approach: | a new benchmark evaluates privacy and security risks in agent–agent interactions . a converse model enables attackers to embed malicious requests within plausible discourse . the model is based on a three-tier taxonomy assessing abstraction quality . |
| Outcome: | ConVerse tests privacy and security risks in agent–agent interactions with 12 user personas and over 864 contextually grounded attacks. |