5 papers
The Alchemy of Thought: Understanding In-Context Learning Through Supervised Classification
Harshita Narnoli, Mihai Surdeanu
In-context learning (ICL) has become a prominent paradigm to rapidly customize LLMs to new tasks without fine-tuning. However, despite the empirical evidence of its usefulness, we…
Can LLMs Judge Debates? Evaluating Non-Linear Reasoning via Argumentation Theory Semantics
Reza Sanayei, Srdjan Vesic, Eduardo Blanco +1
Large Language Models (LLMs) excel at linear reasoning tasks but remain underexplored on non-linear structures such as those found in natural debates, which are best expressed as a…
Towards Compute-Optimal Many-Shot In-Context Learning
Shahriar Golchin, Yanfei Chen, Rujun Han +7
Long-context large language models (LLMs) are able to process inputs containing up to several million tokens. In the scope of in-context learning (ICL), this translates into using…
Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models
Enfa Fane, Mihai Surdeanu, Eduardo Blanco +1
Understanding how news narratives frame entities is crucial for studying media's impact on societal perceptions of events. In this paper, we evaluate the zero-shot capabilities of…
Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization
Portia Cooper, Harshita Narnoli, Mihai Surdeanu
Text-to-image models are vulnerable to the stepwise "Divide-and-Conquer Attack" (DACA) that utilize a large language model to obfuscate inappropriate content in prompts by wrapping…