7 papers
SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agents
Qianfeng Wen, Yifan Simon Liu, Xin Liu +4
Generative Engine Optimization (GEO) lets content owners rewrite web content to increase their visibility in generative systems. In recommendation agents, this creates a risk that…
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement
Difan Jiao, Qianfeng Wen, Blair Yang +2
We introduce ThinkTwice, a simple two-phase framework that jointly optimizes LLMs to solve reasoning problems and refine the answers, based on Group Relative Policy Optimization (G…
OasisSimp: An Open-source Asian-English Sentence Simplification Dataset
Hannah Liu, Muxin Tian, Iqra Ali +8
Sentence simplification aims to make complex text more accessible by reducing linguistic complexity while preserving the original meaning. However, progress in this area remains li…
Grounded Chess Reasoning in Language Models via Master Distillation
Zhenwei Tang, Qianfeng Wen, Seth Grief-Albert +4
Language models often lack grounded reasoning capabilities in specialized domains where training data is scarce but bespoke systems excel. We introduce a general framework for dist…
SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications?
Muxin Tian, Zhe Wang, Blair Yang +7
Can large language model agents develop industry-level mobile applications? We introduce \textbf{SWE-Bench Mobile}, a benchmark for evaluating coding agents on realistic software e…
SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
Zhenwei Tang, Difan Jiao, Blair Yang +1
Evaluating whether vision-language models (VLMs) reason consistently across representations is challenging because modality comparisons are typically confounded by task differences…
Report Cards: Qualitative Evaluation of Language Models Using Natural Language Summaries
Blair Yang, Fuyang Cui, Keiran Paster +4
The rapid development and dynamic nature of large language models (LLMs) make it difficult for conventional quantitative benchmarks to accurately assess their capabilities. We prop…