Publications

Identifying birdsong syllables without labelled data
Mélisande Teng
Julien Boussard
David Rolnick
Hugo Larochelle
Identifying sequences of syllables within birdsongs is key to tackling a wide array of challenges, including bird individual identification … (see more)and better understanding of animal communication and sensory-motor learning. Recently, machine learning approaches have demonstrated great potential to alleviate the need for experts to label long audio recordings by hand. However, they still typically rely on the availability of labelled data for model training, restricting applicability to a few species and datasets. In this work, we build the first fully unsupervised algorithm to decompose birdsong recordings into sequences of syllables. We first detect syllable events, then cluster them to extract templates -- syllable representations -- before performing matching pursuit to decompose the recording as a sequence of syllables. We evaluate our automatic annotations against human labels on a dataset of Bengalese finch songs and find that our unsupervised method achieves high performance. We also demonstrate that our approach can distinguish individual birds within a species through their unique vocal signatures, for both Bengalese finches and another species, the great tit.
2025-09-22
ArXiv (preprint)
arxiv.org
arxiv.org
Intrinsic Meets Extrinsic Fairness: Assessing the Downstream Impact of Bias Mitigation in Large Language Models
Mina Arzaghi
Alireza Dehghanpour Farashah
Florian Carichon
Golnoosh Farnadi
Large Language Models (LLMs) are increasingly deployed in sensitive domains such as finance, where intrinsic representational biases can pro… (see more)pagate into extrinsic harms in downstream tasks. High-stakes applications such as credit scoring are especially vulnerable, as biased model behavior can reinforce existing inequities and result in harmful disparities across demographic groups \cite{blodgett2020language}. While prior research has questioned whether intrinsic bias truly translates into extrinsic unfairness \cite{goldfarb2020intrinsic}, this connection remains poorly understood. To address this gap, we propose a four-stage evaluation framework that systematically examines the relationship between intrinsic and extrinsic fairness. In Stage 1, we establish a baseline by training models such as logistic regression, LLM embeddings, and fine-tuned classifiers without any mitigation strategy, providing reference points for fairness and accuracy. In Stage 2, we evaluate task-level mitigation through Counterfactual Data Augmentation (CDA) \cite{gallegos2024bias}, which balances gender representation by generating counterfactual training instances, allowing us to assess improvements in extrinsic fairness. In Stage 3, we adapt concept unlearning \cite{dige2024mitigating} as an intrinsic bias mitigation method, encouraging LLMs to forget socioeconomic stereotypes while preserving fluency and predictive utility, and we evaluate how this intervention impacts downstream fairness. Finally, in Stage 4, we combine CDA with unlearning to test whether dual mitigation further enhances fairness. We conduct experiments on three datasets (Adult Census Income, ACS Employment, and German Credit) using instruction-tuned LLMs (LLaMA-3.1, Phi-3, and Gemma-2) in both frozen embedding and fine-tuned classifier settings, evaluating performance with predictive accuracy and group fairness metrics, including Demographic Parity, Accuracy Parity, and Equality of Odds. Our experiments demonstrate that intrinsic bias mitigation through unlearning is highly effective; in Phi-3, for instance, it reduces gender socioeconomic stereotype gaps by 94.9\% while maintaining language fluency. In downstream tasks, unlearning consistently improves group fairness metrics while preserving predictive accuracy, whereas CDA primarily enhances demographic parity but can introduce accuracy trade-offs. For instance, on the ACS Employment dataset, unlearned Gemma-2 improved Accuracy Parity from 0.199 to 0.104 (48\% gain), and combining CDA with unlearning on Llama-3.1 reduced Demographic Parity from 0.080 to 0.014 (82\% gain). On the Adult dataset, all three models maintained accuracy above 0.82 while showing reduced fairness gaps, and on German Credit, unlearning consistently outperformed CDA by improving group fairness metrics without sacrificing predictive performance. Overall, CDA and unlearning exhibit complementary effects, with their combination yielding the strongest fairness improvements across models and datasets. This work contributes to bias mitigation and fairness in LLMs in two ways. First, we adapt concept unlearning to mitigate socioeconomic stereotyping, showing that intrinsic bias reduction improves both representational and downstream fairness. Second, we introduce a unified evaluation framework that links intrinsic and extrinsic fairness, enabling systematic comparison of mitigation strategies. The framework is flexible, applying to both fine-tuned and frozen LLMs, and offers actionable guidance for deploying fairer models in finance and other high-stakes domains.
2025-09-22
NeurIPS.cc/2025/Workshop/WiML (published)
openreview.net
openreview.net
Neither Valid Nor Reliable? Investigating the Use of LLMs as Judges
Khaoula Chehbouni
Mohammed Haddou
Jackie Cheung
Golnoosh Farnadi
2025-09-22
NeurIPS.cc/2025/Workshop/WiML (published)
openreview.net
openreview.net
Reasoning with Preference Constraints: A Benchmark for Language Models in Many-to-One Matching Markets
Marylou Fauchard
Florian Carichon
Margarida Carvalho
Golnoosh Farnadi
2025-09-22
NeurIPS.cc/2025/Workshop/WiML (published)
doi.org
openreview.net
Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models
Istabrak Abbes
Gopeshh Subbaraj
Matthew D Riemer
Nizar Islah
Benjamin Therien
Tsuguchika Tabaru
Hiroaki Kingetsu
Sarath Chandar
Irina Rish
2025-09-22
NeurIPS.cc/2025/Workshop/WiML (published)
doi.org
openreview.net
Reward the Reward Designer: Making Reinforcement Learning Useful for Clinical Decision Making
Sumana Basu
Adriana Romero Soriano
Doina Precup
2025-09-22
NeurIPS.cc/2025/Workshop/WiML (published)
openreview.net
openreview.net
Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework
Cléa Chataigner
Rebecca Ma
Prakhar Ganesh
Afaf Taïk
Elliot Creager
Golnoosh Farnadi
2025-09-22
NeurIPS.cc/2025/Workshop/WiML (published)
openreview.net
openreview.net
Towards Democratizing LLMs: Investigating Multilingual Mixture-of-Experts Models
Aditi Khandelwal
Marius Mosbach
Verna Dankers
Siva Reddy
Golnoosh Farnadi
2025-09-22
NeurIPS.cc/2025/Workshop/WiML (published)
openreview.net
openreview.net
Towards a generalizable, unified framework for decoding from multimodal neural activity
Nanda H Krishna
Mathys Loiselle
Avery Hee-Woon Ryoo
Matt Perich
Guillaume Lajoie
Recent advances in neural decoding have led to the development of large-scale deep learning-based neural decoders that can generalize across… (see more) sessions and subjects. However, existing approaches predominantly focus on single modalities of neural activity, limiting their applicability to specific modalities and tasks. In this work, we present a multimodal extension of the POYO framework that jointly processes neuronal spikes and local field potentials (LFPs) for behavioural decoding. Our approach employs flexible tokenization schemes for both spikes and LFPs, enabling efficient processing of heterogeneous neural populations without preprocessing requirements like binning. Through experiments on data from nonhuman primates performing motor tasks, we demonstrate that multimodal pretraining yields superior decoding performance compared to unimodal baselines. We also show evidence of cross-modal transfer: models pretrained on both modalities outperform LFP-only models when fine-tuned solely on LFPs, suggesting a path toward more cost-effective brain-computer interfaces that can use performant LFP-based decoders. Our models also exhibit robustness to missing modalities during inference when trained with modality masking, and scale effectively with both model size and pretraining data. Overall, this work represents an important first step towards unified, general-purpose neural decoders capable of leveraging diverse neural signals for a variety of brain-computer interface applications.
2025-09-22
NeurIPS.cc/2025/Workshop/BrainBodyFM (published)
openreview.net
openreview.net
Unifying Mechanistic Interpretations of Neural Networks Trained on Modular Addition
Gabriela Moisescu-Pareja
Gavin McCracken
Vincent Létourneau
Doina Precup
Jonathan Love
2025-09-22
NeurIPS.cc/2025/Workshop/WiML (published)
openreview.net
openreview.net
Virtual Consistency for Audio Editing
Matthieu Cervera
Francesco Paissan
Mirco Ravanelli
Cem Subakan
Free-form, text-based audio editing remains a persistent challenge, despite progress in inversion-based neural methods. Current approaches r… (see more)ely on slow inversion procedures, limiting their practicality. We present a virtual-consistency based audio editing system that bypasses inversion by adapting the sampling process of diffusion models. Our pipeline is model-agnostic, requiring no fine-tuning or architectural changes, and achieves substantial speed-ups over recent neural editing baselines. Crucially, it achieves this efficiency without compromising quality, as demonstrated by quantitative benchmarks and a user study involving 16 participants.
2025-09-21
ArXiv (preprint)
doi.org
arxiv.org
Virtual Consistency for Audio Editing
Matthieu Cervera
Francesco Paissan
Mirco Ravanelli
Cem Subakan
Free-form, text-based audio editing remains a persistent challenge, despite progress in inversion-based neural methods. Current approaches r… (see more)ely on slow inversion procedures, limiting their practicality. We present a virtual-consistency based audio editing system that bypasses inversion by adapting the sampling process of diffusion models. Our pipeline is model-agnostic, requiring no fine-tuning or architectural changes, and achieves substantial speed-ups over recent neural editing baselines. Crucially, it achieves this efficiency without compromising quality, as demonstrated by quantitative benchmarks and a user study involving 16 participants.
2025-09-21
ArXiv (preprint)
arxiv.org
arxiv.org