9 papers
Just Ask for a Table: A Thirty-Token User Prompt Defeats Sponsored Recommendations in Twelve LLMs
Andreas Maier, Jeta Sopa, Gozde Gul Sahin +2
Wu et al. (2026) showed that most frontier large language models (LLMs) recommend a sponsored, roughly twice-as-expensive flight when their system prompt contains a soft sponsorshi…
FormalRewardBench: A Benchmark for Formal Theorem Proving Reward Models
Zeynel A. UluÅan, Burak S. Akbudak, Can S. Erer +1
Recent neural theorem provers use reinforcement learning with verifiable rewards (RLVR), where proof assistants provide binary correctness signals. While verifiable rewards are che…
Visual Reasoning through Tool-supervised Reinforcement Learning
Qihua Dong, Gozde Sahin, Pei Wang +4
In this paper, we investigate the problem of how to effectively master tool-use to solve complex visual reasoning tasks for Multimodal Large Language Models. To achieve that, we pr…
Instructional Text Across Disciplines: A Survey of Representations, Downstream Tasks, and Open Challenges Toward Capable AI Agents
Abdulfattah Safa, Tamta Kapanadze, Arda UzunoÄlu +1
Recent advances in large language models have demonstrated promising capabilities in following simple instructions through instruction tuning. However, real-world tasks often invol…
Cetvel: A Unified Benchmark for Evaluating Language Understanding, Generation and Cultural Capacity of LLMs for Turkish
Yakup Abrek Er, Ilker Kesen, Gözde Gül Åahin +1
We introduce Cetvel, a comprehensive benchmark designed to evaluate large language models (LLMs) in Turkish. Existing Turkish benchmarks often lack either task diversity or cultura…
A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding
Abdulfattah Safa, Gözde Gül Åahin
Dialogue State Tracking (DST) is crucial for understanding user needs and executing appropriate system actions in task-oriented dialogues. Majority of existing DST methods are desi…