565 citations · 653 across the 28 of their papers we have counts for
7 papers · 1 filter
LiteraryTaste: A Preference Dataset for Creative Writing Personalization
John Joon Young Chung, Vishakh Padmakumar, Melissa Roemmele +7
People have different creative writing preferences, and large language models (LLMs) for these tasks can benefit from adapting to each user's preferences. However, these models are…
Intent-Aware Schema Generation And Refinement For Literature Review Tables
Vishakh Padmakumar, Joseph Chee Chang, Kyle Lo +2
The increasing volume of academic literature makes it essential for researchers to organize, compare, and contrast collections of documents. Large language models (LLMs) can suppor…
Principled Content Selection to Generate Diverse and Personalized Multi-Document Summaries
Vishakh Padmakumar, Zichao Wang, David Arbour +1
While large language models (LLMs) are increasingly capable of handling longer contexts, recent work has demonstrated that they exhibit the "lost in the middle" phenomenon (Liu et…
Evaluating the Diversity and Quality of LLM Generated Content
Alexander Shypula, Shuo Li, Botong Zhang +3
Recent work suggests that preference-tuning techniques -- such as Reinforcement Learning from Human Feedback (RLHF) methods like PPO and GRPO, as well as alternatives like DPO -- r…
Measuring LLM Novelty As The Frontier Of Original And High-Quality Output
Vishakh Padmakumar, Chen Yueh-Han, Jane Pan +2
As large language models (LLMs) are increasingly used for ideation and scientific discovery, it is important to evaluate their ability to generate novel output. Prior work evaluate…
Modifying Large Language Model Post-Training for Diverse Creative Writing
John Joon Young Chung, Vishakh Padmakumar, Melissa Roemmele +2
As creative writing tasks do not have singular correct answers, large language models (LLMs) trained to perform these tasks should be able to generate diverse valid outputs. Howeve…
Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas
Nishant Balepur, Vishakh Padmakumar, Fumeng Yang +3
LLMs are aligned to follow input instructions by learning which of two responses users prefer for a prompt. However, such preference data do not convey why users prefer responses t…