8 papers
Compositional Consistency-Guided Decoding for Three-Way Logical Question Answering
Tianyi Huang, Ming Hou, Jiaheng Su +2
Three-way logical question answering (QA) assigns one of , , or to a hypothesis given a premise set . We study this task as a com…
Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems
Tianyi Huang, Samuel Xu, Jason Tansong Dang +2
Agentic systems often fail not by being entirely wrong, but by being too precise: a response may be generally useful while particular claims exceed what the evidence supports. We s…
PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs
Tianyi Huang, Caden Yang, Emily Yin +2
Retrieval-augmented language models can retrieve relevant evidence yet still commit to answers before explicitly checking whether the retrieved context supports the conclusion. We…
Permutation-Consensus Listwise Judging for Robust Factuality Evaluation
Tianyi Huang, Nathan Huang, Justin Tang +2
Large language models (LLMs) are now widely used as judges, yet their decisions can change under presentation choices that should be irrelevant. We study one such source of instabi…
CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering
Tianyi Huang, Ying Kai Deng
In factual question answering, many errors are not failures of access but failures of commitment: the system retrieves relevant evidence, yet still settles on the wrong answer. We…
Structured Reasoning for Fairness: A Multi-Agent Approach to Bias Detection in Textual Data
Tianyi Huang, Elsa Fan
From disinformation spread by AI chatbots to AI recommendations that inadvertently reinforce stereotypes, textual bias poses a significant challenge to the trustworthiness of large…
Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent Approach
Tianyi Huang, Arya Somasundaram
Large Language Models (LLMs) often perpetuate biases in pronoun usage, leading to misrepresentation or exclusion of queer individuals. This paper addresses the specific problem of…
FEAD: Figma-Enhanced App Design Framework for Improving UI/UX in Educational App Development
Tianyi Huang
Designing user-centric mobile applications is increasingly essential in educational technology. However, platforms like MIT App Inventor-one of the world's largest educational app…