6 accepted papers
Prompts used in recent large language model based applications are often fixed and lengthy, leading to significant computational overhead. To address this challenge, we propose Generative Prompt Internalization (GenPI), a lightweight method that employs a joint training approach. GenPI not only repl…
Using large teacher models to guide the training of smaller student models has become the prevailing paradigm for efficient and effective learning. However, vocabulary mismatches between teacher and student language models pose significant challenges in language modeling, resulting in divergent toke…
As language models (LMs) become capable of handling a wide range of tasks, their evaluation is becoming as challenging as their development. Most generation benchmarks currently assess LMs using abstract evaluation criteria-like helpfulness and harmlessness-which often lack the flexibility and granu…
We introduce a new problem KTRL+F, a knowledge-augmented in-document search that necessitates real-time identification of all semantic targets within a document with the awareness of external sources through a single natural query. KTRL+F addresses following unique challenges for in-document search:…
The more new features that are being added to smartphones, the harder it becomes for users to find them. This is because the feature names are usually short and there are just too many of them for the users to remember the exact words. The users are more comfortable asking contextual queries that d…
The Situated Interactive Multi-Modal Conversations (SIMMC) 2.0 aims to create virtual shopping assistants that can accept complex multi-modal inputs, i.e. visual appearances of objects and user utterances. It consists of four subtasks, multi-modal disambiguation (MM-Disamb), multi-modal coreference…