8 papers
Two routes to the Hadamard condition
Eleanor March
In quantum field theory on curved spacetime, the Hadamard condition is often presented as a necessary condition on 'physically reasonable', 'vacuum-like' states of linear quantum f…
Nudgeability: Reasoning Models Follow Confidence Signals Without Tracking Their Own Competence
Rohit Saxena, Utkarsh Upadhyay
Reasoning language models that can call tools must decide during inference whether to answer unaided or delegate. Any self-reflection mechanism for this must answer three questions…
Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered
Aryo Pradipta Gema, Neel Rajani, Rohit Saxena +2
Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness tests often place explicit bia…
Do Composed Image Retrieval Benchmarks Require Multimodal Composition?
Matteo Attimonelli, Alessandro De Bellis, Aryo Pradipta Gema +8
Composed Image Retrieval (CIR) is a multimodal retrieval task where a query consists of a reference image and a textual modification, and the goal is to retrieve a target image sat…
VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models
Rohit Saxena, Alessandro Suglia, Pasquale Minervini
Vision-language models (VLMs) achieve strong performance on standard, high-quality datasets, but we still do not fully understand how they perform under real-world image distortion…
Analyzing LLM Instruction Optimization for Tabular Fact Verification
Xiaotang Du, Giwon Hong, Wai-Chung Kwan +4
Instruction optimization provides a lightweight, model-agnostic approach to enhancing the reasoning performance of large language models (LLMs). This paper presents the first syste…
Enhancing Long Document Long Form Summarisation with Self-Planning
Xiaotang Du, Rohit Saxena, Laura Perez-Beltrachini +2
We introduce a novel approach for long context summarisation, highlight-guided generation, that leverages sentence-level information as a content plan to improve the traceability a…
Finding Culture-Sensitive Neurons in Vision-Language Models
Xiutian Zhao, Rochelle Choenni, Rohit Saxena +1
Despite their impressive performance, vision-language models (VLMs) still struggle on culturally situated inputs. To understand how VLMs process culturally grounded information, we…