565 citations · 688 across the 19 of their papers we have counts for
19 papers
Preference Learning Algorithms Do Not Learn Preference Rankings
Angelica Chen, Sadhika Malladi, Lily H. Zhang +4
Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner…
Playing Large Games with Oracles and AI Debate
Xinyi Chen, Angelica Chen, Dean Foster +1
We consider regret minimization in repeated games with a very large number of actions. Such games are inherent in the setting of AI Safety via Debate \cite{irving2018ai}, and more…
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
Angelica Chen, Ravid Shwartz-Ziv, Kyunghyun Cho +2
Most interpretability research in NLP focuses on understanding the behavior and features of a fully trained model. However, certain insights into model behavior may only be accessi…
Latent State Models of Training Dynamics
Michael Y. Hu, Angelica Chen, Naomi Saphra +1
The impact of randomness on model training is poorly understood. How do differences in data order and initialization actually manifest in the model, such that some training runs ou…
Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs
Angelica Chen, Jason Phang, Alicia Parrish +4
Large language models (LLMs) have achieved widespread success on a variety of in-context few-shot tasks, but this success is typically evaluated via correctness rather than consist…
Training Language Models with Language Feedback at Scale
Jérémy Scheurer, Jon Ander Campos, Tomasz Korbak +4
Pretrained language models often generate outputs that are not in line with human preferences, such as harmful text or factually incorrect summaries. Recent work approaches the abo…
Improving Code Generation by Training with Natural Language Feedback
Angelica Chen, Jérémy Scheurer, Tomasz Korbak +5
The potential for pre-trained large language models (LLMs) to use natural language feedback at inference time has been an exciting recent development. We build upon this observatio…
EvoPrompting: Language Models for Code-Level Neural Architecture Search
Angelica Chen, David M. Dohan, David R. So
Given the recent impressive accomplishments of language models (LMs) for code generation, we explore the use of LMs as adaptive mutation and crossover operators for an evolutionary…
Pretraining Language Models with Human Preferences
Tomasz Korbak, Kejian Shi, Angelica Chen +5
Language models (LMs) are pretrained to imitate internet text, including content that would violate human preferences if generated by an LM: falsehoods, offensive comments, persona…
What Do NLP Researchers Believe? Results of the NLP Community Metasurvey
Julian Michael, Ari Holtzman, Alicia Parrish +8
We present the results of the NLP Community Metasurvey. Run from May to June 2022, the survey elicited opinions on controversial issues, including industry influence in the field,…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…
SQuALITY: Building a Long-Document Summarization Dataset the Hard Way
Alex Wang, Richard Yuanzhe Pang, Angelica Chen +2
Summarization datasets are often assembled either by scraping naturally occurring public-domain summaries -- which are nearly always in difficult-to-work-with technical domains --…
Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency Detection
Angelica Chen, Vicky Zayats, Daniel D. Walker +1
In modern interactive speech-based systems, speech is consumed and transcribed incrementally prior to having disfluencies removed. This post-processing step is crucial for producin…
Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions
Alicia Parrish, Harsh Trivedi, Ethan Perez +4
Current QA systems can generate reasonable-sounding yet false answers without explanation or evidence for the generated answer, which is especially problematic when humans cannot r…
Training Language Models with Language Feedback
Jérémy Scheurer, Jon Ander Campos, Jun Shern Chan +3
Pretrained language models often do not perform tasks in ways that are in line with our preferences, e.g., generating offensive text or factually incorrect summaries. Recent work a…
QuALITY: Question Answering with Long Input Texts, Yes!
Richard Yuanzhe Pang, Alicia Parrish, Nitish Joshi +8
To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average lengt…
Adversarially Constructed Evaluation Sets Are More Challenging, but May Not Be Fair
Jason Phang, Angelica Chen, William Huang +1
More capable language models increasingly saturate existing task benchmarks, in some cases outperforming humans. This has left little headroom with which to measure further progres…
BBQ: A Hand-Built Bias Benchmark for Question Answering
Alicia Parrish, Angelica Chen, Nikita Nangia +5
It is well documented that NLP models learn social biases, but little work has been done on how these biases manifest in model outputs for applied tasks like question answering (QA…
Generating Logical Forms from Graph Representations of Text and Entities
Peter Shaw, Philip Massey, Angelica Chen +2
Structured information about entities is critical for many semantic parsing tasks. We present an approach that uses a Graph Neural Network (GNN) architecture to incorporate informa…