User behavior sequences are often driven by stable, high-level intents. Existing intent-aware sequential recommendation methods typically extract intents from derived sequence representations to serve as post-hoc supervisory signals. Although effective, this post-hoc paradigm prevents intents from explicitly participat...
Yi-Fan Shao, Pei-Lin Zhou, Shou-Jin Wang et al.· Proceedings of the 35th ACM...· 0 citations
Steering language models using a set of contrastive representations has been a canonical and computationally efficient method for controlling model behavior. Despite this success in controlling certain model behaviors, the effectiveness of activation steering varies markedly across concepts; the generalization properti...
A Layer-Partitioned Alternating Training (LP-AT) method is presented, which assigns distinct model layers to recognize specific action elements through element-specific low-rank adapters and alternates weight updates across element-specific adapters, reducing cross-task interference while enabling per-adapter hyperpara...
Hao Zheng, Jin-Yi Huang, Tian-Tian Zheng et al.· IEEE International Conferenc...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.