Marco Bonizzato

Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training

Juan David Guerra

2025-07-01

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (published)

Modulation of leg trajectory by transcranial magnetic stimulation during walking

H. Bourgeois

Rose Guay-Hottin

El-Mehdi Meftah

Marina Martinez

D. Barthélemy

2025-07-01

Scientific Reports (published)

Combining cortical and spinal stimulation maximizes improvement of gait after spinal cord injury

Roxanne Drainville

Davide Burchielli

Rose Guay-Hottin

Alexandre Sheasby

Marina Martinez

2025-05-27

bioRxiv (preprint)

Bidirectional Information Flow (BIF) - A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization

Juan David Guerra

Thomas Garbay

Guillaume Lajoie

Hierarchical Gaussian Process (H-GP) models divide problems into different subtasks, allowing for different models to address each part, mak… (see more)ing them well-suited for problems with inherent hierarchical structure. However, typical H-GP models do not fully take advantage of this structure, only sending information up or down the hierarchy. This one-way coupling limits sample efficiency and slows convergence. We propose Bidirectional Information Flow (BIF), an efficient H-GP framework that establishes bidirectional information exchange between parent and child models in H-GPs for online training. BIF retains the modular structure of hierarchical models - the parent combines subtask knowledge from children GPs - while introducing top-down feedback to continually refine children models during online learning. This mutual exchange improves sample efficiency, enables robust training, and allows modular reuse of learned subtask models. BIF outperforms conventional H-GP Bayesian Optimization methods, achieving up to 85% and 5x higher

2025-05-01

arXiv (published)

Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training

Juan David Guerra

2025-01-01

ACL (1) (published)

Robust prior-biased acquisition function for human-in-the-loop Bayesian optimization

Rose Guay-Hottin

Lison Kardassevitch

Hugo Pham

Guillaume Lajoie

2025-01-01

Knowl. Based Syst. (published)

Modulation of leg trajectory by transcranial magnetic stimulation during walking

H. Bourgeois

Rose Guay-Hottin

E.-M. Meftah

M. Martinez

D. Barthélemy

The primary motor cortex is involved in initiation and adaptive control of locomotion. However, the role of the motor cortex in controlling … (see more)gait trajectories remains unclear. In animals, cortical neuromodulation allows for precise control of step height. We hypothesized that a similar control framework applies to humans, whereby cortical stimulation would primarily increase foot elevation. Transcranial magnetic stimulation (TMS) was applied over the motor cortex to assess the involvement of the corticospinal tract over the limb trajectory during human walking. Eight healthy adults (aged 20-32 years) participated in treadmill walking at 1.5 km/h. TMS was applied over the left motor cortex at an intensity of 120% of the threshold to elicit a dorsiflexion of the right ankle during the swing phase of gait. Electromyographic (EMG) measurements and three-dimensional (3D) lower limb kinematics were collected. When delivered during the early swing phase, TMS led to a significant increase in the maximum height of the right toe by a mean of 40.7% ± 14.9% (25.6mm ± 9.4 mm, p = 0.0352) and knee height by 57.8%± 16.8%; (32mm ± 9.3 mm; p = 0.008) across participants. These findings indicate that TMS can influence limb trajectory during walking, highlighting its potential as a tool for studying cortical control of locomotion.

2024-10-23

bioRxiv (preprint)

Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training

Juan David Guerra

As large language models (LLMs) are increasingly deployed across various industries, concerns regarding their reliability, particularly due … (see more)to hallucinations - outputs that are factually inaccurate or irrelevant to user input - have grown. Our research investigates the relationship between the training process and the emergence of hallucinations to address a key gap in existing research that focuses primarily on post hoc detection and mitigation strategies. Using models from the Pythia suite (70M - 12B parameters) and several hallucination detection metrics, we analyze hallucination trends throughout training and explore LLM internal dynamics. We introduce Sensitivity Dropout (SenD), a novel training protocol designed to mitigate hallucinations by reducing variance during training. SenD achieves this by deterministically dropping embedding indices with significant variability, referred to as Sensitive Embedding Indices. In addition, we develop an unsupervised hallucination detection metric, Efficient EigenScore (EES), which approximates the traditional EigenScore at 2x speed. This efficient metric is integrated into our protocol, allowing SenD to be both computationally scalable and effective at reducing hallucinations. Our empirical evaluation demonstrates that our approach improves LLM reliability at test time by up to 40% compared to normal training while also providing an efficient method to improve factual accuracy when adapting LLMs to Wikipedia, Medical, and LegalBench domains.

2024-10-20

ArXiv (preprint)

Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training

Juan David Guerra

As large language models (LLMs) are increasingly deployed across various industries, concerns regarding their reliability, particularly due … (see more)to hallucinations - outputs that are factually inaccurate or irrelevant to user input - have grown. Our research investigates the relationship between the training process and the emergence of hallucinations to address a key gap in existing research that focuses primarily on post hoc detection and mitigation strategies. Using models from the Pythia suite (70M - 12B parameters) and several hallucination detection metrics, we analyze hallucination trends throughout training and explore LLM internal dynamics. We introduce Sensitivity Dropout (SenD), a novel training protocol designed to mitigate hallucinations by reducing variance during training. SenD achieves this by deterministically dropping embedding indices with significant variability, referred to as Sensitive Embedding Indices. In addition, we develop an unsupervised hallucination detection metric, Efficient EigenScore (EES), which approximates the traditional EigenScore at 2x speed. This efficient metric is integrated into our protocol, allowing SenD to be both computationally scalable and effective at reducing hallucinations. Our empirical evaluation demonstrates that our approach improves LLM reliability at test time by up to 40% compared to normal training while also providing an efficient method to improve factual accuracy when adapting LLMs to Wikipedia, Medical, and LegalBench domains.

2024-10-20

ArXiv (preprint)

Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training

Juan David Guerra

2024-10-20

ArXiv (preprint)

Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training

Juan David Guerra

As large language models (LLMs) become increasingly deployed across various industries, concerns regarding their reliability, particularly d… (see more)ue to hallucinations-outputs that are factually inaccurate or irrelevant to user input-have grown. Our research investigates the relationship between the training process and the emergence of hallucinations to address a key gap in existing research that focuses primarily on post hoc detection and mitigation strategies. Using models from the Pythia suite (70M-12B parameters) and several hallucination detection metrics, we analyze hallucination trends throughout training and explore LLM internal dynamics. We introduce SEnsitive Neuron Dropout (SeND), a novel training protocol designed to mitigate hallucinations by reducing variance during training. SeND achieves this by deterministically dropping neurons with significant variability on a dataset, referred to as Sensitive Neurons. In addition, we develop an unsupervised hallucination detection metric, Efficient EigenScore (EES), which approximates the traditional EigenScore in 2x speed. This efficient metric is integrated into our protocol, allowing SeND to be both computationally scalable and effective at reducing hallucinations. Our empirical evaluation demonstrates that our approach improves LLM reliability at test time by up to 40% compared to normal training while also providing an efficient method to improve factual accuracy when adapting LLMs to domains such as Wikipedia and Medical datasets.

2024-10-12

NeurIPS.cc/2024/Workshop/SafeGenAi (poster)