Related papers: PEER: A Collaborative Language Model
Emotional support conversations require more than fluent responses. Supporters need to understand the seeker's situation and emotions, adopt an appropriate strategy, and respond in a natural, human-like manner. Despite advances in large…
This paper describes a collaboration between a mathematician and a compositionist who developed a sequence of collaborative writing assignments for calculus. This sequence of developmentally-appropriate assignments presents peer review as a…
Recently, there has been a surge in the use of generated data to enhance the performance of downstream models, largely due to the advancements in pre-trained language models. However, most prevailing methods trained generative and…
Writing is, by nature, a strategic, adaptive, and more importantly, an iterative process. A crucial part of writing is editing and revising the text. Previous works on text revision have focused on defining edit intention taxonomies within…
Evaluation of text generation to date has primarily focused on content created sequentially, rather than improvements on a piece of text. Writing, however, is naturally an iterative and incremental process that requires expertise in…
Peer review is a key component of the publishing process in most fields of science. The increasing submission rates put a strain on reviewing quality and efficiency, motivating the development of applications to support the reviewing and…
Pre-trained Transformers have enabled impressive breakthroughs in generating long and fluent text, yet their outputs are often "rambling" without coherently arranged content. In this work, we present a novel content-controlled text…
Most existing sequence generation models produce outputs in one pass, usually left-to-right. However, this is in contrast with a more natural approach that humans use in generating content; iterative refinement and editing. Recent work has…
Document editing has become a pervasive component of the production of information, with version control systems enabling edits to be efficiently stored and applied. In light of this, the task of learning distributed representations of…
Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor…
Collaborative edition is achieved by distinct sites that work independently on (a copy of) a shared document. Conflicts may arise during this process and must be solved by the collaborative editor. In pure Peer to Peer collaborative…
When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are…
Powerful large language models have facilitated the development of writing assistants that promise to significantly improve the quality and efficiency of composition and communication. However, a barrier to effective assistance is the lack…
In recent years, peer learning has gained attention as a method that promotes spontaneous thinking among learners, and its effectiveness has been confirmed by numerous studies. This study aims to develop an AI Agent as a learning companion…
Language enables humans to share knowledge, reason about the world, and pass on strategies for survival and innovation across generations. At the heart of this process is not just the ability to communicate but also the remarkable…
Multi-task learning is increasingly used to investigate the association structure between multiple responses and a single set of predictor variables in many applications. In the era of big data, the coexistence of incomplete outcomes, large…
We introduce GIER (Gap-driven Iterative Enhancement of Responses), a general framework for improving large language model (LLM) outputs through self-reflection and revision based on conceptual quality criteria. Unlike prompting strategies…
Conversational Agents (CAs) acting as peer supporters have been widely studied and demonstrated beneficial for people's mental health. However, previous peer support CAs either are user-initiated or follow predefined rules to initiate the…
We introduce the task of automatically revising scientific papers based on peer feedback and release ARIES, a dataset of review comments and their corresponding paper edits. The data is drawn from real reviewer-author interactions from…
Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…