Synthical logo
Synthical
Your space
Profile
Activity
Favorites
Folders
Feeds
All articles
Contacts
About
Simple
Original

Articles by Eric Wallace

Trading Inference-Time Compute for Adversarial Robustness
31 January 2025 by Wojciech Zaremba and others
Machine Learning, Cryptography and Security
Deliberative Alignment: Reasoning Enables Safer Language Models
8 January 2025 by Melody Guan and others
Computation and Language, Artificial Intelligence
JAK inhibition decreases the autoimmune burden in Down syndrome
31 December 2024 by A. Rachubinski and others
Genetic and Genomic Medicine
OpenAI o1 System Card
21 December 2024 by Openai and others
Artificial Intelligence
Predicting Emergent Capabilities by Finetuning
25 November 2024 by Charlie Snell and others
Machine Learning, Computation and Language
GPT-4o System Card
25 October 2024 by Openai and others
Computation and Language, Artificial Intelligence
What Evidence Do Language Models Find Convincing?
9 August 2024 by Alexander Wan and others
Computation and Language, Machine Learning
SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
31 July 2024 by Sewon Min and others
Computation and Language, Artificial Intelligence
Shared decision-making interventions in the choice of antipsychotic prescription in people living with psychosis (SHAPE): protocol for a realist review
25 July 2024 by I. Fitzgerald and others
Psychiatry and Clinical Psychology
Privacy Side Channels in Machine Learning Systems
18 July 2024 by Edoardo Debenedetti and others
Cryptography and Security, Machine Learning
Stealing Part of a Production Language Model
2
9 July 2024 by Nicholas Carlini and others at LogoUniversity of Washington
Cryptography and Security
Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
28 June 2024 by Danny Halawi and others at LogoUC Berkeley
Cryptography and Security, Artificial Intelligence
Unfamiliar Finetuning Examples Control How Language Models Hallucinate
28 May 2024 by Katie Kang and others at LogoUC Berkeley
Machine Learning, Artificial Intelligence
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
19 April 2024 by Eric Wallace and others
Cryptography and Security, Computation and Language
Scalable Extraction of Training Data from (Production) Language Models
1
28 November 2023 by Milad Nasr and others at LogoUniversity of Washington
Machine Learning, Computation and Language
Large Language Models Struggle to Learn Long-Tail Knowledge
27 July 2023 by Nikhil Kandpal and others
Computation and Language, Machine Learning
The False Promise of Imitating Proprietary LLMs
25 May 2023 by Arnav Gudibande and others
Computation and Language
The impact of lidocaine plaster prescribing reduction strategies: a comparison of two national health services in Europe
11 May 2023 by Maria Mattsson and others
Pharmacology and Therapeutics
Measuring Forgetting of Memorized Training Examples
9 May 2023 by Matthew Jagielski and others
Machine Learning
Poisoning Language Models During Instruction Tuning
1 May 2023 by Alexander Wan and others
Computation and Language, Cryptography and Security
Trustworthy AI Inference Systems: An Industry Research View
10 February 2023 by Rosario Cammarota and others
Cryptography and Security, Artificial Intelligence
Extracting Training Data from Diffusion Models
30 January 2023 by Nicholas Carlini and others at LogoUC Berkeley
Cryptography and Security, Computer Vision and Pattern Recognition
Medication Safety Incidents Associated with the Remote Delivery of Primary Care: A Rapid Review
18 October 2022 by L. Gleeson and others at LogoUniversity College Dublin
Primary Care Research
Analyzing Dynamic Adversarial Training Data in the Limit
26 September 2022 by Eric Wallace and others at LogoUC Berkeley
Computation and Language, Machine Learning
Automated Crossword Solving
3 July 2022 by Eric Wallace and others
Computation and Language
InCoder: A Generative Model for Code Infilling and Synthesis
17 April 2022 by Daniel Fried and others
Software Engineering, Computation and Language
Deduplicating Training Data Mitigates Privacy Risks in Language Models
16 February 2022 by Nikhil Kandpal and others
Cryptography and Security, Computation and Language
A rapid pharmacogenomic assay to detect NAT2 polymorphisms and guide isoniazid dosingfor tuberculosis treatment
10 August 2021 by Rekha Verma and others at LogoStanford University
Infectious Diseases
Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models
1 July 2021 by Robert L. Logan Iv and others
Computation and Language, Machine Learning
Extracting Training Data from Large Language Models
15 June 2021 by Nicholas Carlini and others
Cryptography and Security, Computation and Language
Load more