RW
Robert West
cs.CLcs.AIcs.CYcs.SIcs.LGcs.DLcs.HCcs.IRcs.CRstat.ML
On Valency
published · living versionsW_wdhdfah8·v1 · currentpublished
From Cookies to Cooks: Insights on Dietary Patterns via Analysis of Web Usage Logs
with Ryen W. White, Eric Horvitz
1 version
Preprints & journals
167 papers in the corpus · 2013–2026Author Correction: On the conversational persuasiveness of GPT-4.42693269 · Salvi, Francesco, Horta Ribeiro, Manoel, Gallotti, Riccardo et al.2026 · 1 citationNature human behaviour. 2026;10(10):2047
Diff Mining: Logit Differences Reveal Finetuning Objectives2608.26462v1 · Greg Kocher, Robert West, Cl'ement Dumas et al.2026 · 0 citationsarXiv
Synthetic Persona Pretraining: Alignment from Token Zero2608.13482v1 · Julian Minder, Viktor Moskvoretskii, Raghav Singhal et al.2026 · 0 citationsarXiv
A reporting checklist for large language models in behavioural science.42265331 · Feuerriegel, Stefan, Barrie, Christopher, Crockett, M J et al.2026 · 16 citationsNature human behaviour. 2026;10(7):1182-1186
Tandem Reinforcement Learning with Verifiable Rewards2606.28166v2 · Difan Jiao, Raghav Singhal, Robert West et al.2026 · 0 citationsarXiv
A narrowing window to understand AI.42241535 · Horvitz, Eric, West, Robert2026 · 1 citationScience (New York, N.Y.). 2026;392(6802):1003
Tracing Persona Vectors Through LLM Pretraining2605.13329v1 · Viktor Moskvoretskii, Dominik Glandorf, Jorge Medina Moreira et al.2026 · 0 citationsarXiv
Integrating Machine-Generated Short Descriptions into the Wikipedia Android App: A Pilot Deployment of Descartes2601.07631v1 · Marija Sakota, Dmitry Brant, Cooltey Feng et al.2026 · 0 citationsarXiv
TiME: Tiny Monolingual Encoders for Efficient NLP Pipelines2512.14645v1 · David Schulmeister, Valentin Hartmann, Lars Klein et al.2025 · 0 citationsarXiv
Carrot, stick, or both? Price incentives for sustainable food choice in competitive environments2512.13174v1 · Francesco Salvi, Giuseppe Russo, Adam Barla et al.2025 · 0 citationsarXiv
Cmprsr: Abstractive Token-Level Question-Agnostic Prompt Compressor2511.12281v2 · Ivan Zakazov, Berke Argin, Oussama Gabouj et al.2025 · 0 citationsarXiv
From Model Training to Model Raising2511.09287v2 · Roland Aydin, Christian Cyron, Steve Bachelor et al.2025 · 0 citationsarXiv
The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation2511.02687v2 · Tim R. Davidson, Adam Fourney, Saleema Amershi et al.2025 · 0 citationsarXiv
SynthWorlds: Controlled Parallel Worlds for Disentangling Reasoning and Knowledge in Language Models2510.24427v3 · Ken Gu, Advait Bhat, Mike A Merrill et al.2025 · 0 citationsarXiv
Tandem Training for Language Models2510.13551v2 · Robert West, Ashton Anderson, Ece Kamar et al.2025 · 0 citationsProceedings of the 2026 Conference of the European Chapter of the Association for Computational Linguistics (EACL)
Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences2510.13900v3 · Julian Minder, Cl'ement Dumas, Stewart Slocum et al.2025 · 0 citationsarXiv
Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification2510.11408v2 · Stefan Krsteski, Giuseppe Russo, Serina Chang et al.2025 · 0 citationsarXiv
GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning2510.01165v1 · Oussama Gabouj, Kamel Charaf, Ivan Zakazov et al.2025 · 0 citationsarXiv
Interactive Evaluation of Large Language Models for Multi-Requirement Software Engineering Tasks2508.18905v1 · Dimitrios Rontogiannis, Maxime Peyrard, Nicolas Baldwin et al.2025 · 0 citationsarXiv
TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards2507.18618v1 · Andreea Nica, Ivan Zakazov, Nicolas Mario Baldwin et al.2025 · 0 citationsarXiv
Quotegraph: A Social Network Extracted from Millions of News Quotations2507.17626v2 · Marko Culjak, Robert West, Andreas Spitz et al.2025 · 0 citationsarXiv
RL for Reasoning by Adaptively Revealing Rationales2506.18110v2 · Mohammad Hossein Amani, Aryo Lotfi, Nicolas Mario Baldwin et al.2025 · 0 citationsarXiv
Combining Constrained and Unconstrained Decoding via Boosting: BoostCD and Its Application to Information Extraction2506.14901v2 · Marija Sakota, Robert West2025 · 1 citationarXiv
zip2zip: Inference-Time Adaptive Tokenization via Online Compression2506.01084v2 · Saibo Geng, Nathan Ranchin, Yunzhen yao et al.2025 · 1 citationarXiv
On the conversational persuasiveness of GPT-4.40389594 · Salvi, Francesco, Horta Ribeiro, Manoel, Gallotti, Riccardo et al.2025 · 282 citationsNature human behaviour. 2025;9(8):1645-1653
Web2Wiki: Characterizing Wikipedia Linking Across the Web2505.15837v1 · Veniamin Veselovsky, Tiziano Piccardi, Ashton Anderson et al.2025 · 0 citationsarXiv
Does Content Moderation Lead Users Away from Fringe Movements? Evidence from a Recovery Community2505.03772v1 · Giuseppe Russo, Maciej Styczen, Manoel Horta Ribeiro et al.2025 · 1 citationarXiv
Localized Cultural Knowledge is Conserved and Controllable in Large Language Models2504.10191v1 · Veniamin Veselovsky, Berke Argin, Benedikt Stroebl et al.2025 · 0 citationsarXiv
Meat-Free Day Reduces Greenhouse Gas Emissions but Poses Challenges for Customer Retention and Adherence to Dietary Guidelines2504.02899v1 · Giuseppe Russo, Kristina Gligori'c, Vincent Moreau et al.2025 · 3 citationsarXiv
Controlling Latent Diffusion Using Latent CLIP2503.08455v1 · Jason Becker, Chris Wendler, Peter Baylies et al.2025 · 0 citationsarXiv
JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models2501.10868v3 · Saibo Geng, Hudson Cooper, MichałMoskal et al.2025 · 3 citationsarXiv
Navigating Knowledge: Patterns and Insights from Wikipedia Consumption2501.00939v1 · Tiziano Piccardi, Robert West2025 · 0 citationsarXiv
Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans?2412.16772v3 · Ivan Zakazov, Mikolaj Boronski, Lorenzo Drudi et al.2024 · 1 citationarXiv
Byte BPE Tokenization as an Inverse string Homomorphism2412.03160v1 · Saibo Geng, Sankalp Gambhir, Chris Wendler et al.2024 · 0 citationsarXiv
Post Guidance for Online Communities2411.16814v2 · Manoel Horta Ribeiro, Robert West, Ryan Lewis et al.2024 · 5 citationsarXiv
Food choice mimicry on a large university campus.39677365 · Gligorić, Kristina, Chiolero, Arnaud, Kıcıman, Emre et al.2025 · 7 citationsPNAS nexus. 2024;3(12):pgae517
Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers2411.08745v4 · Cl'ement Dumas, Chris Wendler, Veniamin Veselovsky et al.2024 · 1 citationarXiv
Controllable Context Sensitivity and the Knob Behind It2411.07404v4 · Julian Minder, Kevin Du, Niklas Stoehr et al.2024 · 1 citationarXiv
Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks2411.04468v1 · Adam Fourney, Gagan Bansal, Hussein Mozannar et al.2024 · 17 citationsarXiv
One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models2410.22366v5 · Viacheslav Surkov, Chris Wendler, Antonio Mari et al.2024 · 1 citationarXiv
Activation Scaling for Steering and Interpreting Language Models2410.04962v1 · Niklas Stoehr, Kevin Du, V'esteinn Sn\aebjarnarson et al.2024 · 5 citationsarXiv
Entity Insertion in Multilingual Linked Corpora: The Case of Wikipedia2410.04254v1 · Tom'as Feith, Akhil Arora, Martin Gerlach et al.2024 · 1 citationarXiv
A Logical Fallacy-Informed Framework for Argument Generation2408.03618v4 · Luca Mouchel, Debjit Paul, Shaobo Cui et al.2024 · 5 citationsarXiv
Self-Recognition in Language Models2407.06946v2 · Tim R. Davidson, Viacheslav Surkov, Veniamin Veselovsky et al.2024 · 2 citationsarXiv
Measuring and shaping the nutritional environment via food sales logs: case studies of campus-wide food choice and a call to action.38899323 · Gligorić, Kristina, Zbinden, Robin, Chiolero, Arnaud et al.2024 · 0 citationsFrontiers in nutrition. 2024;11:1231070
The AI Alignment Paradox2405.20806v2 · Robert West, Roland Aydin2024 · 2 citationsarXiv
Fleet of Agents: Coordinated Problem Solving with Large Language Models2405.06691v3 · Lars Klein, Nearchos Potamitis, Roland Aydin et al.2024 · 0 citationsarXiv
The AI Review Lottery: Widespread AI-Assisted Peer Reviews Boost Paper Scores and Acceptance Rates2405.02150v1 · Giuseppe Russo Latona, Manoel Horta Ribeiro, Tim R. Davidson et al.2024 · 25 citationsarXiv
Edisum: Summarizing and Explaining Wikipedia Edits at Scale2404.03428v2 · Marija Sakota, Isaac Johnson, Guosheng Feng et al.2024 · 0 citationsarXiv
Can Language Models Recognize Convincing Arguments?2404.00750v2 · Paula Rescala, Manoel Horta Ribeiro, Tiancheng Hu et al.2024 · 11 citationsarXiv
Career total: 270 works. 167 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.