334 citations · 784 across the 20 of their papers we have counts for
20 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…
Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
Narmeen Oozeer, Luke Marks, Shreyans Jain +2
Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of…
Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use
Anna Goldie, Azalia Mirhoseini, Hao Zhou +2
Reinforcement learning has been shown to improve the performance of large language models. However, traditional approaches like RLHF or RLAIF treat the problem as single-step. As f…
Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models
Caia Costello, Simon Guo, Anna Goldie +1
Large language models (LLMs) have demonstrated strong capabilities in programming and mathematical reasoning tasks, but are constrained by limited high-quality training data. Synth…
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…
That Chip Has Sailed: A Critique of Unfounded Skepticism Around AI for Chip Design
Anna Goldie, Azalia Mirhoseini, Jeff Dean
In 2020, we introduced a deep reinforcement learning method capable of generating superhuman chip layouts, which we then published in Nature and open-sourced on GitHub. AlphaChip h…
Specific versus General Principles for Constitutional AI
Sandipan Kundu, Yuntao Bai, Saurav Kadavath +33
Human feedback can prevent overtly harmful utterances in conversational models, but may not automatically mitigate subtle problematic behaviors such as a stated desire for self-pre…
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…
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…
Delving into Macro Placement with Reinforcement Learning
Zixuan Jiang, Ebrahim Songhori, Shen Wang +5
In physical design, human designers typically place macros via trial and error, which is a Markov decision process. Reinforcement learning (RL) methods have demonstrated superhuman…
A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators
Dan Zhang, Safeen Huda, Ebrahim Songhori +4
The rapidly-changing deep learning landscape presents a unique opportunity for building inference accelerators optimized for specific datacenter-scale workloads. We propose Full-st…
Transferable Graph Optimizers for ML Compilers
Yanqi Zhou, Sudip Roy, Amirali Abdolrashidi +9
Most compilers for machine learning (ML) frameworks need to solve many correlated optimization problems to generate efficient machine code. Current ML compilers rely on heuristics…
Chip Placement with Deep Reinforcement Learning
Azalia Mirhoseini, Anna Goldie, Mustafa Yazgan +19
In this work, we present a learning-based approach to chip placement, one of the most complex and time-consuming stages of the chip design process. Unlike prior methods, our approa…
Placement Optimization with Deep Reinforcement Learning
Anna Goldie, Azalia Mirhoseini
Placement Optimization is an important problem in systems and chip design, which consists of mapping the nodes of a graph onto a limited set of resources to optimize for an objecti…
Generalized Clustering by Learning to Optimize Expected Normalized Cuts
Azade Nazi, Will Hang, Anna Goldie +2
We introduce a novel end-to-end approach for learning to cluster in the absence of labeled examples. Our clustering objective is based on optimizing normalized cuts, a criterion wh…
GDP: Generalized Device Placement for Dataflow Graphs
Yanqi Zhou, Sudip Roy, Amirali Abdolrashidi +8
Runtime and scalability of large neural networks can be significantly affected by the placement of operations in their dataflow graphs on suitable devices. With increasingly comple…
GAP: Generalizable Approximate Graph Partitioning Framework
Azade Nazi, Will Hang, Anna Goldie +2
Graph partitioning is the problem of dividing the nodes of a graph into balanced partitions while minimizing the edge cut across the partitions. Due to its combinatorial nature, ma…
Massive Exploration of Neural Machine Translation Architectures
Denny Britz, Anna Goldie, Minh-Thang Luong +1
Neural Machine Translation (NMT) has shown remarkable progress over the past few years with production systems now being deployed to end-users. One major drawback of current archit…
Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models
Louis Shao, Stephan Gouws, Denny Britz +3
Sequence-to-sequence models have been applied to the conversation response generation problem where the source sequence is the conversation history and the target sequence is the r…