1 citations · 2 across the 11 of their papers we have counts for
13 papers
Diffusion Language Models for Perplexity-Aware Black-Box Attacks
Ali Al-Lawati, Elsayed Eshra, Dongwon Lee +1
\emph{Continuous-space} attacks find prompts that trigger malicious behaviors, such as overthinking, in black-box LLMs by sampling or optimizing over a low-dimensional Gaussian lat…
Quantifying Behavioral Tails in Black-Box Language Models
Elsayed Eshra, Ali Al-Lawati, Dongwon Lee +1
We introduce RareTrap, a framework for estimating the probability of severe behaviors in black box large language models (LLMs). A key challenge for probability estimation is defin…
Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models
Fali Wang, Ali Al-Lawati, Iliyas Bektas +5
Graph reasoning provides a promising testbed for evaluating the reasoning ability of large language models (LLMs), as graph instances can be programmatically generated, structurall…
LLM Benchmark Datasets Should Be Contamination-Resistant
Ali Al-Lawati, Jason Lucas, Dongwon Lee +1
Benchmark datasets are critical for reproducible, reliable, and discriminative evaluation of LLMs. However, recent studies reveal that many benchmark datasets are included in pretr…
Moderation by Interrogation: Uncovering Concealed Intent in Agent Social Networks
Ali Al-Lawati, Nafis Tripto, Abolfazl Ansari +4
The emergence of multi-agent systems introduces novel moderation challenges that extend beyond content filtering. Agents with may contribute content tha…
DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects
Jason Lucas, Matt Murtagh, Ali Al-Lawati +3
Harmful content detectors, particularly disinformation classifiers, are predominantly developed and evaluated on Standard American English (SAE), leaving their robustness to dialec…
BLUFF: Benchmarking the Detection of False and Synthetic Content across 58 Low-Resource Languages
Jason Lucas, Matt Murtagh-White, Adaku Uchendu +6
Multilingual falsehoods threaten information integrity worldwide, yet detection benchmarks remain confined to English or a few high-resource languages, leaving low-resource linguis…
Do Multimodal RAG Systems Leak Data? A Comprehensive Evaluation of Membership Inference and Image Caption Retrieval Attacks
Ali Al-Lawati, Suhang Wang
The growing adoption of multimodal Retrieval-Augmented Generation (mRAG) pipelines for vision-centric tasks (e.g., visual QA) introduces important privacy challenges. In particular…
A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness
Fali Wang, Jihai Chen, Shuhua Yang +4
Large language models (LLMs) have achieved remarkable progress across domains and applications but face challenges such as high fine-tuning costs, inference latency, limited edge d…
Graph-based Molecular In-context Learning Grounded on Morgan Fingerprints
Ali Al-Lawati, Jason Lucas, Zhiwei Zhang +2
In-context learning (ICL) effectively conditions large language models (LLMs) for molecular tasks, such as property prediction and molecule captioning, by embedding carefully selec…
Semantic Captioning: Benchmark Dataset and Graph-Aware Few-Shot In-Context Learning for SQL2Text
Ali Al-Lawati, Jason Lucas, Prasenjit Mitra
Large Language Models (LLMs) have demonstrated remarkable performance in various NLP tasks, including semantic parsing, which translates natural language into formal code represent…
WildGraph: Realistic Graph-based Trajectory Generation for Wildlife
Ali Al-Lawati, Elsayed Eshra, Prasenjit Mitra
Trajectory generation is an important task in movement studies; it circumvents the privacy, ethical, and technical challenges of collecting real trajectories from the target popula…
WildGEN: Long-horizon Trajectory Generation for Wildlife
Ali Al-Lawati, Elsayed Eshra, Prasenjit Mitra
Trajectory generation is an important concern in pedestrian, vehicle, and wildlife movement studies. Generated trajectories help enrich the training corpus in relation to deep lear…