39 citations · 116 across the 35 of their papers we have counts for
39 papers
Training Reasoning Models to Generate Diverse Scientific Ideas
Manya Wadhwa, Pranav Narayanan Venkit, Hiroaki Hayashi +3
One of the first steps of a research pipeline is generating ideas. Large Language Models (LLMs) are increasingly used to automate this step, but most of this work optimizes the qua…
Generative AI floods and dilutes the market for books
Tuhin Chakrabarty, Xinyue Liu, Jane C. Ginsburg +1
Generative AI can produce book-length works of fiction at near-zero cost. These books are often dismissed as low-quality ``slop'' that buyers will ignore, and are assumed to carry…
Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models
Xinyue Liu, Niloofar Mireshghallah, Jane C. Ginsburg +1
Frontier LLM companies have repeatedly assured courts and regulators that their models do not store copies of training data. They further rely on safety alignment strategies via RL…
Can Good Writing Be Generative? Expert-Level AI Writing Emerges through Fine-Tuning on High-Quality Books
Tuhin Chakrabarty, Paramveer S. Dhillon
Creative writing has long been considered a uniquely human endeavor, requiring voice and style that machines could not replicate. This assumption is challenged by Generative AI tha…
Readers Prefer Outputs of AI Trained on Copyrighted Books over Expert Human Writers
Tuhin Chakrabarty, Jane C. Ginsburg, Paramveer Dhillon
The use of copyrighted books for training AI has sparked lawsuits from authors concerned about AI generating derivative content. Yet whether these models can produce high-quality l…
Death of the Novel(ty): Beyond n-Gram Novelty as a Metric for Textual Creativity
Arkadiy Saakyan, Najoung Kim, Smaranda Muresan +1
N-gram novelty is widely used to evaluate language models' ability to generate text outside of their training data. More recently, it has also been adopted as a metric for measurin…
Measuring AI "Slop" in Text
Chantal Shaib, Tuhin Chakrabarty, Diego Garcia-Olano +1
AI "slop" is an increasingly popular term used to describe low-quality AI-generated text, but there is currently no agreed upon definition of this term nor a means to measure its o…
Facilitating Longitudinal Interaction Studies of AI Systems
Tao Long, Sitong Wang, Émilie Fabre +14
UIST researchers develop tools to address user challenges. However, user interactions with AI evolve over time through learning, adaptation, and repurposing, making one time evalua…
AI Safety Should Prioritize the Future of Work
Sanchaita Hazra, Bodhisattwa Prasad Majumder, Tuhin Chakrabarty
Current efforts in AI safety prioritize filtering harmful content, preventing manipulation of human behavior, and eliminating existential risks in cybersecurity or biosecurity. Whi…
AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation
Tuhin Chakrabarty, Philippe Laban, Chien-Sheng Wu
AI-generated text is proliferating across domains, from creative writing and journalism to marketing content and scientific articles. Models can follow user-provided instructions t…
How do Humans and Language Models Reason About Creativity? A Comparative Analysis
Antonio Laverghetta, Tuhin Chakrabarty, Tom Hope +3
Creativity assessment in science and engineering is increasingly based on both human and AI judgment, but the cognitive processes and biases behind these evaluations remain poorly…
Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits
Tuhin Chakrabarty, Philippe Laban, Chien-Sheng Wu
LLM-based applications are helping people write, and LLM-generated text is making its way into social media, journalism, and our classrooms. However, the differences between LLM-ge…
Understanding Figurative Meaning through Explainable Visual Entailment
Arkadiy Saakyan, Shreyas Kulkarni, Tuhin Chakrabarty +1
Large Vision-Language Models (VLMs) have demonstrated strong capabilities in tasks requiring a fine-grained understanding of literal meaning in images and text, such as visual ques…
Identifying Self-Disclosures of Use, Misuse and Addiction in Community-based Social Media Posts
Chenghao Yang, Tuhin Chakrabarty, Karli R Hochstatter +3
In the last decade, the United States has lost more than 500,000 people from an overdose involving prescription and illicit opioids making it a national public health emergency (US…
Learning to Follow Object-Centric Image Editing Instructions Faithfully
Tuhin Chakrabarty, Kanishk Singh, Arkadiy Saakyan +1
Natural language instructions are a powerful interface for editing the outputs of text-to-image diffusion models. However, several challenges need to be addressed: 1) underspecific…
Art or Artifice? Large Language Models and the False Promise of Creativity
Tuhin Chakrabarty, Philippe Laban, Divyansh Agarwal +2
Researchers have argued that large language models (LLMs) exhibit high-quality writing capabilities from blogs to stories. However, evaluating objectively the creativity of a piece…
Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writers
Tuhin Chakrabarty, Vishakh Padmakumar, Faeze Brahman +1
The development of large language models (LLMs) capable of following instructions and engaging in conversational interactions sparked increased interest in their utilization across…
I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors
Tuhin Chakrabarty, Arkadiy Saakyan, Olivia Winn +4
Visual metaphors are powerful rhetorical devices used to persuade or communicate creative ideas through images. Similar to linguistic metaphors, they convey meaning implicitly thro…
Multitask Instruction-based Prompting for Fallacy Recognition
Tariq Alhindi, Tuhin Chakrabarty, Elena Musi +1
Fallacies are used as seemingly valid arguments to support a position and persuade the audience about its validity. Recognizing fallacies is an intrinsically difficult task both fo…
Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing
Tuhin Chakrabarty, Vishakh Padmakumar, He He
Recent work in training large language models (LLMs) to follow natural language instructions has opened up exciting opportunities for natural language interface design. Building on…
CONSISTENT: Open-Ended Question Generation From News Articles
Tuhin Chakrabarty, Justin Lewis, Smaranda Muresan
Recent work on question generation has largely focused on factoid questions such as who, what, where, when about basic facts. Generating open-ended why, how, what, etc. questions t…
FLUTE: Figurative Language Understanding through Textual Explanations
Tuhin Chakrabarty, Arkadiy Saakyan, Debanjan Ghosh +1
Figurative language understanding has been recently framed as a recognizing textual entailment (RTE) task (a.k.a. natural language inference, or NLI). However, similar to classical…
Fine-tuned Language Models are Continual Learners
Thomas Scialom, Tuhin Chakrabarty, Smaranda Muresan
Recent work on large language models relies on the intuition that most natural language processing tasks can be described via natural language instructions. Language models trained…
Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models
Tuhin Chakrabarty, Aadit Trivedi, Smaranda Muresan
Enthymemes are defined as arguments where a premise or conclusion is left implicit. We tackle the task of generating the implicit premise in an enthymeme, which requires not only a…