Author name cluster

Nicola Cancedda

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench

Edan Toledo
Karen Hambardzumyan
Martin Josifoski
Rishi Hazra
Nicolas Baldwin
Alexis Audran-Reiss
Michael Kuchnik
Despoina Magka

AI research agents are demonstrating great potential to accelerate scientific progress by automating the design, implementation, and training of machine learning models. We focus on methods for improving agents' performance on MLE-bench, a challenging benchmark where agents compete in Kaggle competitions to solve real-world machine learning problems. We formalize AI research agents as search policies that navigate a space of candidate solutions, iteratively modifying them using operators. By designing and systematically varying different operator sets and search policies (Greedy, MCTS, Evolutionary), we show that their interplay is critical for achieving high performance. Our best pairing of search strategy and operator set achieves a state-of-the-art result on MLE-bench lite, increasing the success rate of achieving a Kaggle medal from 39. 6% to 47. 7%. Our investigation underscores the importance of jointly considering the search strategy, operator design, and evaluation methodology in advancing automated machine learning.

PDF Details

IJCAI Conference 2025 Conference Paper

Combining Code Generating Large Language Models and Self-Play to Iteratively Refine Strategies in Games

Yoram Bachrach
Edan Toledo
Karen Hambardzumyan
Despoina Magka
Martin Josifoski
Minqi Jiang
Jakob Foerster
Roberta Raileanu

We propose a self-play approach to generating strategies for playing in multi-player games, where strategies are represented as computer code. We use large language models (LLMs) to generate pieces of code to play in the game, which we refer to as generated bots. We engage the LLM generated bots in competitions, designed to generate increasingly stronger strategies. We follow game theoretic principles in organizing these tournaments, and use a Policy Space Response Oracle (PSRO) approach. We start with an initial set of LLM generated bots, and continue in rounds for adding new bots into the population. Each round adds a bot to the population by asking the LLM to produce code for playing against a bot representing the Nash equilibrium mixture over the current population. Our analysis shows that even a few rounds are sufficient to produces strong bots for playing the game. Our demo shows the process for the game of Checkers. We allow users to select initial bots in the population, run the process, inspect how the bots evolve over time, and play against the generated bots.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

LLM Unlearning via Neural Activation Redirection

William Shen
Xinchi Qiu
Meghdad Kurmanji
Alexandru-Andrei Iacob
Lorenzo Sani
Yihong Chen
Nicola Cancedda
Nicholas Lane

The ability to selectively remove knowledge from LLMs is highly desirable. However, existing methods often struggle with balancing unlearning efficacy and retain model utility, and lack controllability at inference time to emulate base model behavior as if it had never seen the unlearned data. In this paper, we propose LUNAR, a novel unlearning method grounded in the Linear Representation Hypothesis and operates by redirecting the representations of unlearned data to activation regions that expresses its inability to answer. We show that contrastive features are not a prerequisite for effective activation redirection, and LUNAR achieves state-of-the-art unlearning performance and superior controllability. Specifically, LUNAR achieves between 2. 9x and 11. 7x improvement in the combined unlearning efficacy and model utility score (Deviation Score) across various base models and generates coherent, contextually appropriate responses post-unlearning. Moreover, LUNAR effectively reduces parameter updates to a single down-projection matrix, a novel design that significantly enhances efficiency by 20x and robustness. Finally, we demonstrate that LUNAR is robust to white-box adversarial attacks and versatile in real-world scenarios, including handling sequential unlearning requests.

PDF Details

ICLR Conference 2025 Conference Paper

Robust LLM safeguarding via refusal feature adversarial training

Lei Yu
Virginie Do
Karen Hambardzumyan
Nicola Cancedda

Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful responses. Defending against such attacks remains challenging due to the opacity of jailbreaking mechanisms and the high computational cost of training LLMs robustly. We demonstrate that adversarial attacks share a universal mechanism for circumventing LLM safeguards that works by ablating a dimension in the residual stream embedding space called the refusal feature. We further show that the operation of refusal feature ablation (RFA) approximates the worst-case perturbation of offsetting model safety. Based on these findings, we propose Refusal Feature Adversarial Training (ReFAT), a novel algorithm that efficiently performs LLM adversarial training by simulating the effect of input-level attacks via RFA. Experiment results show that ReFAT significantly improves the robustness of three popular LLMs against a wide range of adversarial attacks, with considerably less computational overhead compared to existing adversarial training methods.

Details

NeurIPS Conference 2023 Conference Paper

Toolformer: Language Models Can Teach Themselves to Use Tools

Timo Schick
Jane Dwivedi-Yu
Roberto Dessi
Roberta Raileanu
Maria Lomeli
Eric Hambro
Luke Zettlemoyer
Nicola Cancedda

Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale. They also, paradoxically, struggle with basic functionality, such as arithmetic or factual lookup, where much simpler and smaller specialized models excel. In this paper, we show that LMs can teach themselves to use external tools via simple APIs and achieve the best of both worlds. We introduce Toolformer, a model trained to decide which APIs to call, when to call them, what arguments to pass, and how to best incorporate the results into future token prediction. This is done in a self-supervised way, requiring nothing more than a handful of demonstrations for each API. We incorporate a range of tools, including a calculator, a Q&A system, a search engine, a translation system, and a calendar. Toolformer achieves substantially improved zero-shot performance across a variety of downstream tasks, often competitive with much larger models, without sacrificing its core language modeling abilities.

PDF Details

JMLR Journal 2003 Journal Article

Word-Sequence Kernels

Nicola Cancedda
Eric Gaussier
Cyril Goutte
Jean-Michel Renders

We address the problem of categorising documents using kernel-based methods such as Support Vector Machines. Since the work of Joachims (1998), there is ample experimental evidence that SVM using the standard word frequencies as features yield state-of-the-art performance on a number of benchmark problems. Recently, Lodhi et al. (2002) proposed the use of string kernels, a novel way of computing document similarity based of matching non-consecutive subsequences of characters. In this article, we propose the use of this technique with sequences of words rather than characters. This approach has several advantages, in particular it is more efficient computationally and it ties in closely with standard linguistic pre-processing techniques. We present some extensions to sequence kernels dealing with symbol-dependent and match-dependent decay factors, and present empirical evaluations of these extensions on the Reuters-21578 datasets.

PDF Details