Multi-agent LLM systems increasingly automate tasks involving agents with different levels of privilege, creating a security risk in which a compromised low-privilege agent can influence a higher-privilege agent and trigger an unauthorized action. We study attack propagation in a four-agent LangGraph pipeline comprisin...
Tanzim Hossain Safin, Sharif Noor Zisad, S. Shatabda et al.· 0 citations
Evolving documents, such as laws, tax codes, and software documentation, are amended, replaced, and sometimes reverted over time, so a question has different correct answers at different dates. In contrast to encyclopedic knowledge, where an old fact is simply overwritten, an amendment is itself an official text that s...
M. Sobhani, Md. Faiyaz Abdullah Sayeedi, F. Chowdhury et al.· 1 citation· ⚡1
Idiomatic expressions are an integral part of natural language, reflecting cultural nuances and posing unique challenges for computational models, particularly in low-resource languages. In this paper, we present the first large-scale benchmark dataset of Bangla idioms, complemented by a synthetic multiple-choice quest...
Mousumi Akter, Md. Faiyaz Abdullah Sayeedi, Nurul Labib Sayeedi et al.· 0 citations
Fine-tuning can improve legal question-answering accuracy without improving how models use law supplied in context. We study this distinction in bilingual Bangladeshi legal QA, where observed errors can arise from answer scoring, retrieval, or failure to use relevant law. We construct a hierarchy-preserving statutory c...
A representation-accessibility analysis of frozen genomic language models across regulatory, epigenetic, promoter, splice-site, and variant-effect prediction tasks shows that local biological signal is partially present in frozen representations, but is not always accessible through final pooled embeddings.
Nirjhor Datta, Swakkhar Shatabda, M. Rahman· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
