6 citations · 14 across the 20 of their papers we have counts for
20 papers
Estimating Tail Risks in Language Model Output Distributions
Rico Angell, Raghav Singhal, Zachary Horvitz +4
Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of these models is increasingly high-stakes. Fortunatel…
Factuality on Demand: Controlling the Factuality-Informativeness Trade-off in Text Generation
Ziwei Gong, Yanda Chen, Julia Hirschberg +4
Large language models (LLMs) encode knowledge with varying degrees of confidence. When responding to queries, models face an inherent trade-off: they can generate responses that ar…
Exploring Chain-of-Thought Reasoning for Steerable Pluralistic Alignment
Yunfan Zhang, Kathleen McKeown, Smaranda Muresan
Large Language Models (LLMs) are typically trained to reflect a relatively uniform set of values, which limits their applicability to tasks that require understanding of nuanced hu…
Rethinking Reasoning with MDLMs: Early Exits, Post-hoc Reasoning, and Beyond
Zachary Horvitz, Raghav Singhal, Hao Zou +4
The reasoning paradigm, where language models reason before answering, has enabled breakthroughs on tasks such as mathematical problem-solving. While current tooling for reasoning…
iBERT: Interpretable Embeddings via Sense Decomposition
Vishal Anand, Milad Alshomary, Kathleen McKeown
We present iBERT (interpretable-BERT), an encoder to produce inherently interpretable and controllable embeddings - designed to modularize and expose the discriminative cues presen…
ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges
Cheng Qian, Hongyi Du, Hongru Wang +6
Recent progress in large language models (LLMs) has enabled substantial advances in solving mathematical problems. However, existing benchmarks often fail to reflect the complexity…
DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning
Borui Wang, Kathleen McKeown, Rex Ying
Reinforcement learning from expert demonstrations has long remained a challenging research problem, and existing state-of-the-art methods using behavioral cloning plus further RL t…
Forecasting Conversation Derailments Through Generation
Yunfan Zhang, Kathleen McKeown, Smaranda Muresan
Forecasting conversation derailment can be useful in real-world settings such as online content moderation, conflict resolution, and business negotiations. However, despite languag…
Layered Insights: Generalizable Analysis of Authorial Style by Leveraging All Transformer Layers
Milad Alshomary, Nikhil Reddy Varimalla, Vishal Anand +2
We propose a new approach for the authorship attribution task that leverages the various linguistic representations learned at different layers of pre-trained transformer-based mod…
The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination
Yuji Zhang, Sha Li, Cheng Qian +8
Hallucination is a persistent challenge in large language models (LLMs), where even with rigorous quality control, models often generate distorted facts. This paradox, in which err…
A General Framework for Inference-time Scaling and Steering of Diffusion Models
Raghav Singhal, Zachary Horvitz, Ryan Teehan +4
Diffusion models produce impressive results in modalities ranging from images and video to protein design and text. However, generating samples with user-specified properties remai…
StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples
Ajay Patel, Jiacheng Zhu, Justin Qiu +4
Style representations aim to embed texts with similar writing styles closely and texts with different styles far apart, regardless of content. However, the contrastive triplets oft…
Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution
Milad Alshomary, Narutatsu Ri, Marianna Apidianaki +3
Recent state-of-the-art authorship attribution methods learn authorship representations of texts in a latent, non-interpretable space, hindering their usability in real-world appli…
MASIVE: Open-Ended Affective State Identification in English and Spanish
Nicholas Deas, Elsbeth Turcan, Iván Pérez Mejía +1
In the field of emotion analysis, much NLP research focuses on identifying a limited number of discrete emotion categories, often applied across languages. These basic sets, howeve…
Solving Zebra Puzzles Using Constraint-Guided Multi-Agent Systems
Shmuel Berman, Kathleen McKeown, Baishakhi Ray
Prior research has enhanced the ability of Large Language Models (LLMs) to solve logic puzzles using techniques such as chain-of-thought prompting or introducing a symbolic represe…
TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings
Zachary Horvitz, Ajay Patel, Kanishk Singh +3
The goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style. Existing style trans…
Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models
Zachary Horvitz, Jingru Chen, Rahul Aditya +4
Humor is a fundamental facet of human cognition and interaction. Yet, despite recent advances in natural language processing, humor detection remains a challenging task that is com…
Social Orientation: A New Feature for Dialogue Analysis
Todd Morrill, Zhaoyuan Deng, Yanda Chen +3
There are many settings where it is useful to predict and explain the success or failure of a dialogue. Circumplex theory from psychology models the social orientations (e.g., Warm…
Parallel Structures in Pre-training Data Yield In-Context Learning
Yanda Chen, Chen Zhao, Zhou Yu +2
Pre-trained language models (LMs) are capable of in-context learning (ICL): they can adapt to a task with only a few examples given in the prompt without any parameter update. Howe…
Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation
Kung-Hsiang Huang, Kathleen McKeown, Preslav Nakov +2
Despite recent advances in detecting fake news generated by neural models, their results are not readily applicable to effective detection of human-written disinformation. What lim…