作者位次 #2/6ICLR 2026Poster· Applications / Language, Speech and Dialog
Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
Mohammad Tavakoli · Alireza Salemi · Carrie Ye · Mohamed Abdalla · Hamed Zamani · J Mitchell
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Mohammad Tavakoli · Alireza Salemi · Carrie Ye · Mohamed Abdalla · Hamed Zamani · J Mitchell
Alireza Salemi · Hamed Zamani
Personalization is crucial for enhancing both the effectiveness and user satisfaction of language technologies, particularly in information-seeking tasks like question answering. Current approaches for personalizing large language models (LLMs) often rely on retrieval-augmented generation (RAG),...
To Eun Kim · Alireza Salemi · Hamed Zamani · Fernando Diaz
Modern information access ecosystems consist of mixtures of systems, such as retrieval systems and large language models, and increasingly rely on marketplaces to mediate access to models, tools, and data, making competition between systems inherent to deployment. In such settings, outcomes are s...
Maryam Amirizaniani · Alireza Salemi · Hamed Zamani
Personalization in Question Answering (QA) requires answers that are both accurate and aligned with users' background, preferences, and historical context. Existing state-of-the-art methods primarily rely on retrieval-augmented generation (RAG) solutions that construct personal context by retriev...