6 papers
What We Observe as LLM Behavior Can Be a Side-effect of Inference Backend
Shahed Masoudian, Passant Shafaei, Monorama Swain +1
Benchmark scores are reported as properties of a model, yet the inference framework used to produce them, such as HuggingFace, vLLM, or Ollama, are considered non-influential and t…
Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG
Passant Elchafei, Monorama Swain, Shahed Masoudian +1
Retrieval-Augmented Generation (RAG) aims to reduce hallucination by grounding answers in retrieved evidence, yet hallucinated answers remain common even when relevant documents ar…
Robust Harmful Meme Detection under Missing Modalities via Shared Representation Learning
Felix Breiteneder, Mohammad Belal, Muhammad Saad Saeed +5
Internet memes are powerful tools for communication, capable of spreading political, psychological, and sociocultural ideas. However, they can be harmful and can be used to dissemi…
Investigating Gender Bias in LLM-Generated Stories via Psychological Stereotypes
Shahed Masoudian, Gustavo Escobedo, Hannah Strauss +1
As Large Language Models (LLMs) are increasingly used across different applications, concerns about their potential to amplify gender biases in various tasks are rising. Prior rese…
Just Ask for Music (JAM): Multimodal and Personalized Natural Language Music Recommendation
Alessandro B. Melchiorre, Elena V. Epure, Shahed Masoudian +4
Natural language interfaces offer a compelling approach for music recommendation, enabling users to express complex preferences conversationally. While Large Language Models (LLMs)…
Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization
Shahed Masoudian, Markus Frohmann, Navid Rekabsaz +1
Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-t…