7 citations · 19 across the 34 of their papers we have counts for
40 papers
Homogenization in Multi-Agent Systems
Prakhar Ganesh, Kyra Wilson, Luca Zappella +4
Multi-agent systems (MAS) leverage interactions between agents to perform complex tasks. Despite their success, we show that these interactions can also lead to homogenization, i.e…
Normalized Rewards for Preference Optimization
Shawn Im, Federico Danieli, Skyler Seto +2
Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences. However, DAAs have been observed to over-optimize their…
Theoretical Limits of Language Model Alignment
Lucas Monteiro Paes, Natalie Mackraz, Barry-John Theobald +1
Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common alignment approaches are (i)…
DSO: Direct Steering Optimization for Bias Mitigation
Lucas Monteiro Paes, Nivedha Sivakumar, Yinong Oliver Wang +4
Generative models are often deployed to make decisions on behalf of users, such as vision-language models (VLMs) identifying which person in a room is a doctor to help visually imp…
Bias after Prompting: Persistent Discrimination in Large Language Models
Nivedha Sivakumar, Natalie Mackraz, Samira Khorshidi +4
A dangerous assumption that can be made from prior work on the bias transfer hypothesis (BTH) is that biases do not transfer from pre-trained large language models (LLMs) to adapte…
Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution
Falaah Arif Khan, Nivedha Sivakumar, Yinong Oliver Wang +5
Large language models (LLMs) have achieved impressive performance, leading to their widespread adoption as decision-support tools in resource-constrained contexts like hiring and a…
Fairness Dynamics During Training
Krishna Patel, Nivedha Sivakumar, Barry-John Theobald +2
We investigate fairness dynamics during Large Language Model (LLM) training to enable the diagnoses of biases and mitigations through training interventions like early stopping; we…
Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
Chen Huang, Skyler Seto, Hadi Pouransari +6
Vision foundation models pre-trained on massive data encode rich representations of real-world concepts, which can be adapted to downstream tasks by fine-tuning. However, fine-tuni…
Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs
Yinong Oliver Wang, Nivedha Sivakumar, Falaah Arif Khan +6
The recent rapid adoption of large language models (LLMs) highlights the critical need for benchmarking their fairness. Conventional fairness metrics, which focus on discrete accur…
Aligning LLMs by Predicting Preferences from User Writing Samples
Stéphane Aroca-Ouellette, Natalie Mackraz, Barry-John Theobald +1
Accommodating human preferences is essential for creating aligned LLM agents that deliver personalized and effective interactions. Recent work has shown the potential for LLMs acti…
Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models
Anirudh Sundar, Sinead Williamson, Katherine Metcalf +3
Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically…
ExpertLens: Activation steering features are highly interpretable
Masha Fedzechkina, Eleonora Gualdoni, Sinead Williamson +3
Activation steering methods in large language models (LLMs) have emerged as an effective way to perform targeted updates to enhance generated language without requiring large amoun…
Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models
Natalie Mackraz, Nivedha Sivakumar, Samira Khorshidi +4
Large language models (LLMs) are increasingly being adapted to achieve task-specificity for deployment in real-world decision systems. Several previous works have investigated the…
PREDICT: Preference Reasoning by Evaluating Decomposed preferences Inferred from Candidate Trajectories
Stephane Aroca-Ouellette, Natalie Mackraz, Barry-John Theobald +1
Accommodating human preferences is essential for creating AI agents that deliver personalized and effective interactions. Recent work has shown the potential for LLMs to infer pref…
On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization
Yong Lin, Skyler Seto, Maartje ter Hoeve +6
Reinforcement Learning from Human Feedback (RLHF) is an effective approach for aligning language models to human preferences. Central to RLHF is learning a reward function for scor…
Learning Spatially-Aware Language and Audio Embeddings
Bhavika Devnani, Skyler Seto, Zakaria Aldeneh +5
Humans can picture a sound scene given an imprecise natural language description. For example, it is easy to imagine an acoustic environment given a phrase like "the lion roar came…
Speaker-IPL: Unsupervised Learning of Speaker Characteristics with i-Vector based Pseudo-Labels
Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung +6
Iterative self-training, or iterative pseudo-labeling (IPL) -- using an improved model from the current iteration to provide pseudo-labels for the next iteration -- has proven to b…
Exploring Prediction Targets in Masked Pre-Training for Speech Foundation Models
Li-Wei Chen, Takuya Higuchi, He Bai +6
Speech foundation models, such as HuBERT and its variants, are pre-trained on large amounts of unlabeled speech data and then used for a range of downstream tasks. These models use…
Towards Automatic Assessment of Self-Supervised Speech Models using Rank
Zakaria Aldeneh, Vimal Thilak, Takuya Higuchi +2
This study explores using embedding rank as an unsupervised evaluation metric for general-purpose speech encoders trained via self-supervised learning (SSL). Traditionally, assessi…
Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards
Katherine Metcalf, Miguel Sarabia, Natalie Mackraz +1
Preference-based reinforcement learning (PbRL) aligns a robot behavior with human preferences via a reward function learned from binary feedback over agent behaviors. We show that…
Can you Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?
Zakaria Aldeneh, Takuya Higuchi, Jee-weon Jung +6
Self-supervised features are typically used in place of filter-bank features in speaker verification models. However, these models were originally designed to ingest filter-bank fe…
ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models
Jee-weon Jung, Wangyou Zhang, Jiatong Shi +5
This paper introduces ESPnet-SPK, a toolkit designed with several objectives for training speaker embedding extractors. First, we provide an open-source platform for researchers in…
REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation
Skyler Seto, Barry-John Theobald, Federico Danieli +2
Fully-test-time adaptation (F-TTA) can mitigate performance loss due to distribution shifts between train and test data (1) without access to the training data, and (2) without kno…
Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learning
Miguel Sarabia, Elena Menyaylenko, Alessandro Toso +7
We present Spatial LibriSpeech, a spatial audio dataset with over 650 hours of 19-channel audio, first-order ambisonics, and optional distractor noise. Spatial LibriSpeech is desig…