PPaperPicks

Thomas L. Griffiths

Princeton University, Department of Psychology, NJ, USA

20 papers at tracked venues · 16 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-5138-7255 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×6ICLR ×4ICML ×3ACL ×2EMNLP ×2AAAI ×1NAACL ×1UAI ×1

Frequent coauthors

Ryan Liu
DBLP profile ↗ORCID search ↗
×3
Veniamin Veselovsky
DBLP profile ↗ORCID search ↗
×2
Jake Snell
DBLP profile ↗ORCID search ↗
×2
Kaiqu Liang
DBLP profile ↗ORCID search ↗
×1
Addison J. Wu
DBLP profile ↗ORCID search ↗
×1
Andrew Nam
DBLP profile ↗ORCID search ↗
×1
Takateru Yamakoshi
DBLP profile ↗ORCID search ↗
×1
Jian-Qiao Zhu
DBLP profile ↗ORCID search ↗
×1
Ruaridh Mon-Williams
DBLP profile ↗ORCID search ↗
×1
Akshara Prabhakar
DBLP profile ↗ORCID search ↗
×1
Gianluca M. Bencomo
DBLP profile ↗ORCID search ↗
×1
Andrea Wynn
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Localized Cultural Knowledge is Conserved and Controllable in Large Language Models
    ACL 2026 ·
    Veniamin Veselovsky
    DBLP profile ↗ORCID search ↗
  2. RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation
    ACL 2026 ·
    Kaiqu Liang
    DBLP profile ↗ORCID search ↗
  3. Are Large Language Models Sensitive to the Motives Behind Communication?
    NeurIPS 2025 ·
    Addison J. Wu
    DBLP profile ↗ORCID search ↗
  4. Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers
    NeurIPS 2025 ·
    Andrew Nam
    DBLP profile ↗ORCID search ↗
  5. Conformal Prediction as Bayesian Quadrature
    ICML 2025 ·
    Jake C. Snell
    DBLP profile ↗ORCID search ↗
  6. Evaluating distillation methods for data-efficient syntax learning
    EMNLP 2025 ·
    Takateru Yamakoshi
    DBLP profile ↗ORCID search ↗
  7. Hindsight Merging: Diverse Data Generation with Language Models
    UAI 2025 ·
    Veniamin Veselovsky
    DBLP profile ↗ORCID search ↗
  8. Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice
    ICLR 2025 ·
    Jian-Qiao Zhu
    DBLP profile ↗ORCID search ↗
  9. Large Language Models Assume People are More Rational than We Really are
    ICLR 2025 ·
    Ryan Liu
    DBLP profile ↗ORCID search ↗
  10. Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
    ICML 2025 ·
    Ryan Liu
    DBLP profile ↗ORCID search ↗
  11. Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)
    NeurIPS 2025 ·
    Ruaridh Mon-Williams
    DBLP profile ↗ORCID search ↗
  12. A Metalearned Neural Circuit for Nonparametric Bayesian Inference
    NeurIPS 2024 ·
    Jake Snell
    DBLP profile ↗ORCID search ↗
  13. Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning
    EMNLP 2024 ·
    Akshara Prabhakar
    DBLP profile ↗ORCID search ↗
  14. How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?
    ICML 2024 ·
    Ryan Liu
    DBLP profile ↗ORCID search ↗
  15. Implicit Maximum a Posteriori Filtering via Adaptive Optimization
    ICLR 2024 ·
    Gianluca M. Bencomo
    DBLP profile ↗ORCID search ↗
  16. Learning Human-like Representations to Enable Learning Human Values
    NeurIPS 2024 ·
    Andrea Wynn
    DBLP profile ↗ORCID search ↗
  17. Learning with Language-Guided State Abstractions
    ICLR 2024 ·
    Andi Peng
    DBLP profile ↗ORCID search ↗
  18. MacGyver: Are Large Language Models Creative Problem Solvers?
    NAACL 2024 ·
    Yufei Tian
    DBLP profile ↗ORCID search ↗
  19. Structurally Guided Task Decomposition in Spatial Navigation Tasks (Student Abstract)
    AAAI 2024 ·
    Ruiqi He
    DBLP profile ↗ORCID search ↗
  20. Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
    NeurIPS 2024 ·
    Declan Campbell
    DBLP profile ↗ORCID search ↗