11 papers
GRCD: Grounded Region Change Detection for Multi-Finding Chest X-Ray Pairs
OFM Riaz Rahman Aranya, Peyman Najafirad, Kevin Desai
Radiologists routinely compare current and prior chest X-rays to track disease progression, producing follow-up reports that describe multiple findings, each localised to an anatom…
Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis
Fatemeh Haji, Javier Delarosa Quiros, Peyman Najafirad
Combinatorial optimization (CO) underlies decision-making from logistics to chip design, where infeasible solutions are operationally unusable and small quality gains translate int…
Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing
Bryce Hinkley, Peyman Najafirad
We study selective refusal editing as a three-way control problem: induce non-refusal on designated edit prompts while preserving benign behavior and harmful refusals outside the e…
Agentic Adversarial Rewriting Exposes Architectural Vulnerabilities in Black-Box NLP Pipelines
Mazal Bethany, Kim-Kwang Raymond Choo, Nishant Vishwamitra +1
Multi-component natural language processing (NLP) pipelines are increasingly deployed for high-stakes decisions, yet no existing adversarial method can test their robustness under…
RASTeR: Robust, Agentic, and Structured Temporal Reasoning
Dan Schumacher, Fatemeh Haji, Tara Grey +7
Temporal question answering (TQA) remains a challenge for large language models (LLMs), particularly when retrieved content may be irrelevant, outdated, or temporally inconsistent.…
Reflective Agreement: Combining Self-Mixture of Agents with a Sequence Tagger for Robust Event Extraction
Fatemeh Haji, Mazal Bethany, Cho-Yu Jason Chiang +2
Event Extraction (EE) involves automatically identifying and extracting structured information about events from unstructured text, including triggers, event types, and arguments.…