8 papers
Pick the Mixture, Not the Samples: Combinatorial Data Selection for LLMs
Luyang Zhang, Jialu Wang, Bebei Li
Data selection for LLM fine-tuning faces two facts about real training: data pools draw from many distinct domains, and evaluation spans diverse tasks. As a result, the same sample…
What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music
Luyang Zhang, Xirui Jiang, Junwei Deng +3
Advances in generative AI are rapidly increasing the quality and commercial value of generated music, and this progress depends on large catalogs of creators' recordings. This rais…
Post-Training Recipe, More Than Model Family, Shapes Multi-Agent LLM Conversational Behavior
Luyang Zhang, Jialu Wang, Fei Xue +1
Multi-LLM systems use multiple language models to deliberate, judge each other's outputs, or coordinate as agents. Their value depends on the models producing measurably different…
Toward Agentic Governance: What Shapes LLM-Agent Intervention in Public Forums?
Luyang Zhang, Yi-Yun Chu, Ramayya Krishnan
LLM agents are increasingly used in moderation-relevant public forum workflows, where their choices to answer, acknowledge, repair, or decline are routinely challenged by users, pl…
Predicting Inference-Time Scaling Gains from Labeled Validation-Set Output Statistics
Luyang Zhang, Jingyan Li
Best-of- inference scaling (drawing candidate answers from a language model and returning the one a reward model ranks highest) improves accuracy by an amount that varies ac…
Do Agents Repair When Challenged -- or Just Reply? Challenge, Repair, and Public Correction in a Deployed Agent Forum
Luyang Zhang, Yi-Yun Chu, Jialu Wang +2
As large language model (LLM) agents enter public forums, a key question is whether those forums sustain challenge, repair, and public correction, or merely produce norm-like langu…
An Economic Framework for Generative Engines: Advertising or Subscription?
Luyang Zhang, Cathy Jiao, Beibei Li +1
Generative Engines (GEs) such as ChatGPT and Google's AI Overviews are rapidly reshaping search economics by delivering synthesized responses that allow users to bypass third-party…
The Power of Linear Programming in Sponsored Listings Ranking: Evidence from a Large-Scale Field Experiment
Haihao Lu, Luyang Zhang, Yuting Zhu
Sponsored product advertisements constitute a major revenue source for online marketplaces such as Amazon, Walmart, and Alibaba. A key operational challenge in these systems lies i…