Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
Multi-Channel Mitigation of Source-Trust Shortcuts in Fact-Checking RL Agents
Jianchang Su, Yiwei Yang, Wei Zhang
Retrieval-augmented fact-checkers often receive a reliability label, such as HIGH or LOW trust, for each evidence source. These labels should adjust the model's confidence and its…
cs.AI2026
Constraints Are Graphs, Not Chains: Exact Decoding for Diffusion Language Models
Jianchang Su, Wei Zhang
Diffusion language models (dLLMs) predict masked positions in arbitrary order, but their exact constrained decoders still encode constraints as sequential languages, whose state mu…
cs.AI2026
When Can First-Order Models of Fine-Tuning Bound Forgetting?
Jianchang Su, Wei Zhang
Fine-tuning a language model on new data can make it forget facts that it should keep. We ask whether measurements taken at the start of a fine-tuning run can bound, for each prote…