publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. calibration-sft.png
    Probabilistic Calibration Is a Trainable Capability in Language Models
    Davide Baldelli, Sruthi Kuriakose, Maryam Hashemzadeh, and 2 more authors
    arXiv preprint arXiv:2605.11845, 2026
    arXiv Code
  2. hangman.jpg
    LLMs Can’t Play Hangman: On the Necessity of a Private Working Memory for Language Agents
    Davide Baldelli, Ali Parviz, Amal Zouaq, and 1 more author
    In Conference on Lifelong Learning Agents (CoLLAs), 2026
    arXiv

2025

  1. cadmium.png
    CADmium: Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design
    Prashant Govindarajan, Davide Baldelli, Jay Pathak, and 2 more authors
    Transactions on Machine Learning Research, 2025
    arXiv Code

2024

  1. twolar.png
    TWOLAR: a two-step LLM-augmented distillation method for passage reranking
    Davide Baldelli, Junfeng Jiang, Akiko Aizawa, and 1 more author
    In European Conference on Information Retrieval, 2024
    arXiv Code