416 citations · 2.1k across the 26 of their papers we have counts for
26 papers
PolyAlign: Conditional Human-Distribution Alignment
L. D. M. S. Sai Teja, Ufaq Khan, Sathira Silva +2
Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective fo…
InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior
Huisheng Wang, Zhuoshi Pan, Hangjing Zhang +3
Aligning Large Language Models (LLMs) with investor decision-making processes under herd behavior is a critical challenge in behavioral finance, which grapples with a fundamental l…
Jailbreak Distillation: Renewable Safety Benchmarking
Jingyu Zhang, Ahmed Elgohary, Xiawei Wang +5
Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a no…
Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactions
Taedong Yun, Eric Yang, Mustafa Safdari +13
We present an end-to-end framework for generating synthetic users for evaluating interactive agents designed to encourage positive behavior changes, such as in health and lifestyle…
The Capacity for Moral Self-Correction in Large Language Models
Deep Ganguli, Amanda Askell, Nicholas Schiefer +46
We test the hypothesis that language models trained with reinforcement learning from human feedback (RLHF) have the capability to "morally self-correct" -- to avoid producing harmf…
Discovering Language Model Behaviors with Model-Written Evaluations
Ethan Perez, Sam Ringer, Kamilė Lukošiūtė +60
As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (w…
Constitutional AI: Harmlessness from AI Feedback
Yuntao Bai, Saurav Kadavath, Sandipan Kundu +48
As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improveme…
Measuring Progress on Scalable Oversight for Large Language Models
Samuel R. Bowman, Jeeyoon Hyun, Ethan Perez +43
Developing safe and useful general-purpose AI systems will require us to make progress on scalable oversight: the problem of supervising systems that potentially outperform us on m…
In-context Learning and Induction Heads
Catherine Olsson, Nelson Elhage, Neel Nanda +23
"Induction heads" are attention heads that implement a simple algorithm to complete token sequences like [A][B] ... [A] -> [B]. In this work, we present preliminary and indirect ev…
Toy Models of Superposition
Nelson Elhage, Tristan Hume, Catherine Olsson +13
Neural networks often pack many unrelated concepts into a single neuron - a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging. This…
Exploring and Evaluating Personalized Models for Code Generation
Andrei Zlotchevski, Dawn Drain, Alexey Svyatkovskiy +3
Large Transformer models achieved the state-of-the-art status for Natural Language Understanding tasks and are increasingly becoming the baseline model architecture for modeling so…
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
Deep Ganguli, Liane Lovitt, Jackson Kernion +33
We describe our early efforts to red team language models in order to simultaneously discover, measure, and attempt to reduce their potentially harmful outputs. We make three main…
Language Models (Mostly) Know What They Know
Saurav Kadavath, Tom Conerly, Amanda Askell +33
We study whether language models can evaluate the validity of their own claims and predict which questions they will be able to answer correctly. We first show that larger models a…
Scaling Laws and Interpretability of Learning from Repeated Data
Danny Hernandez, Tom Brown, Tom Conerly +15
Recent large language models have been trained on vast datasets, but also often on repeated data, either intentionally for the purpose of upweighting higher quality data, or uninte…
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Yuntao Bai, Andy Jones, Kamal Ndousse +28
We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune language models to act as helpful and harmless assistants. We find this alignment tra…
Predictability and Surprise in Large Generative Models
Deep Ganguli, Danny Hernandez, Liane Lovitt +27
Large-scale pre-training has recently emerged as a technique for creating capable, general purpose, generative models such as GPT-3, Megatron-Turing NLG, Gopher, and many others. I…
A General Language Assistant as a Laboratory for Alignment
Amanda Askell, Yuntao Bai, Anna Chen +19
Given the broad capabilities of large language models, it should be possible to work towards a general-purpose, text-based assistant that is aligned with human values, meaning that…
Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy
Colin B. Clement, Shuai Lu, Xiaoyu Liu +5
Statistical language modeling and translation with transformers have found many successful applications in program understanding and generation tasks, setting high benchmarks for t…
Distilling Transformers for Neural Cross-Domain Search
Colin B. Clement, Chen Wu, Dawn Drain +1
Pre-trained transformers have recently clinched top spots in the gamut of natural language tasks and pioneered solutions to software engineering tasks. Even information retrieval h…
DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons
Dawn Drain, Colin B. Clement, Guillermo Serrato +1
The joint task of bug localization and program repair is an integral part of the software development process. In this work we present DeepDebug, an approach to automated debugging…
Generating Bug-Fixes Using Pretrained Transformers
Dawn Drain, Chen Wu, Alexey Svyatkovskiy +1
Detecting and fixing bugs are two of the most important yet frustrating parts of the software development cycle. Existing bug detection tools are based mainly on static analyzers,…
Generating Code with the Help of Retrieved Template Functions and Stack Overflow Answers
Dawn Drain, Changran Hu, Chen Wu +2
We approach the important challenge of code autocompletion as an open-domain task, in which a sequence-to-sequence code generator model is enhanced with the ability to attend to re…
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Shuai Lu, Daya Guo, Shuo Ren +19
Benchmark datasets have a significant impact on accelerating research in programming language tasks. In this paper, we introduce CodeXGLUE, a benchmark dataset to foster machine le…
PyMT5: multi-mode translation of natural language and Python code with transformers
Colin B. Clement, Dawn Drain, Jonathan Timcheck +2
Simultaneously modeling source code and natural language has many exciting applications in automated software development and understanding. Pursuant to achieving such technology,…