Publications

AI content detection in the emerging information ecosystem: new obligations for media and tech companies
Alistair Knott
Dino Pedreschi
Toshiya Jitsuzumi
Susan Leavy
D. Eyers
Tapabrata Chakraborti
Andrew Trotman
Sundar Sundareswaran
Ricardo Baeza-Yates
Przemyslaw Biecek
Adrian Weller
Paul D. Teal
Subhadip Basu
Mehmet Haklidir
Virginia Morini
Stuart Russell
Yoshua Bengio
2024-09-21
Ethics and Information Technology (published)
doi.org
ToxiSight: Insights Towards Detected Chat Toxicity
Zachary Yang
Domenico Tullo
Reihaneh Rabbany
We present a comprehensive explainability dashboard designed for in-game chat toxicity. This dashboard integrates various existing explainab… (see more)le AI (XAI) techniques, including token importance analysis, model output visualization, and attribution to the training dataset. It also provides insights through the closest positive and negative examples, facilitating a deeper understanding and potential correction of the training data. Additionally, the dashboard includes word sense analysis—particularly useful for new moderators—and offers free-text explanations for both positive and negative predictions. This multi-faceted approach enhances the interpretability and transparency of toxicity detection models.
2024-09-21
EMNLP/2024/Workshop/BlackBoxNLP (accepted)
openreview.net
openreview.net
ChainBuddy: An AI Agent System for Generating LLM Pipelines
Jingyue Zhang
Ian Arawjo
2024-09-20
ArXiv (preprint)
doi.org
arxiv.org
Development of small, cost‐efficient scintillating fiber detectors for automated synthesis of positron emission tomography radiopharmaceuticals
Hailey Ahn
Liam Carroll
Robert Hopewell
I-Huang Tsai
Dean Jolly
Gassan Massarweh
Shirin A. Enger
2024-09-20
Medical Physics (Lancaster) (published)
doi.org
Dynamic HumTrans: Humming Transcription Using CNNs and Dynamic Programming
Shubham Gupta
Isaac Neri Gomez-Sarmiento
Faez Amjed Mezdari
Mirco Ravanelli
Cem Subakan
2024-09-19
Lecture Notes in Computer Science (published)
doi.org
arxiv.org
Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data
Jiaming Zhou
Abbas Ghaddar
Ge Zhang
Liheng Ma
Yaochen Hu
Soumyasundar Pal
Mark Coates
Bin Wang
Yingxue Zhang
Jianye Hao
2024-09-19
ArXiv (preprint)
doi.org
arxiv.org
Explaining Network Decision Provides Insights on the Causal Interaction Between Brain Regions in a Motor Imagery Task
Davide Borra
Mirco Ravanelli
2024-09-19
Lecture Notes in Computer Science (published)
doi.org
Multi-modal Decoding of Reach-to-Grasping from EEG and EMG via Neural Networks
Davide Borra
Matteo Fraternali
Mirco Ravanelli
Elisa Magosso
2024-09-19
Lecture Notes in Computer Science (published)
doi.org
Relative biological effectiveness of clinically relevant photon energies for the survival of human colorectal, cervical, and prostate cancer cell lines
Joanna Li
N. Chabaytah
Joud Babik
Behnaz Behmand
H. Bekerat
Tanner Connell
Michael D C Evans
Russell Ruo
T. Vuong
Shirin A. Enger
2024-09-19
Physics in Medicine & Biology (published)
doi.org
Training Language Models to Self-Correct via Reinforcement Learning
Aviral Kumar
Vincent Zhuang
Rishabh Agarwal
Yi Su
John D Co-Reyes
Avi Singh
Kate Baumli
Shariq N Iqbal
Colton Bishop
Rebecca Roelofs
Lei M Zhang
Kay McKinney
Disha Shrivastava
Cosmin Paduraru
George Tucker
Doina Precup
Feryal Behbahani
Aleksandra Faust
Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffecti… (see more)ve in modern LLMs. Existing approaches for training self-correction either require multiple models or rely on a more capable model or other forms of supervision. To this end, we develop a multi-turn online reinforcement learning (RL) approach, SCoRe, that significantly improves an LLM's self-correction ability using entirely self-generated data. To build SCoRe, we first show that variants of supervised fine-tuning (SFT) on offline model-generated correction traces are insufficient for instilling self-correction behavior. In particular, we observe that training via SFT either suffers from a distribution mismatch between the training data and the model's own responses or implicitly prefers only a certain mode of correction behavior that is often not effective at test time. SCoRe addresses these challenges by training under the model's own distribution of self-generated correction traces and using appropriate regularization to steer the learning process into learning a self-correction strategy that is effective at test time as opposed to simply fitting high-reward responses for a given prompt. This regularization prescribes running a first phase of RL on a base model to generate a policy initialization that is less susceptible to collapse and then using a reward bonus to amplify self-correction during training. When applied to Gemini 1.0 Pro and 1.5 Flash models, we find that SCoRe achieves state-of-the-art self-correction performance, improving the base models' self-correction by 15.6% and 9.1% respectively on the MATH and HumanEval benchmarks.
2024-09-19
ArXiv (preprint)
doi.org
arxiv.org
Understanding Web Application Workloads and Their Applications: Systematic Literature Review and Characterization
Roozbeh Aghili
Qiaolin Qin
Heng Li
Foutse Khomh
2024-09-18
ArXiv (preprint)
doi.org
arxiv.org
An Attentive Approach for Building Partial Reasoning Agents from Pixels
Safa Alver
Doina Precup
We study the problem of building reasoning agents that are able to generalize in an effective manner. Towards this goal, we propose an end-t… (see more)o-end approach for building model-based reinforcement learning agents that dynamically focus their reasoning to the relevant aspects of the environment: after automatically identifying the distinct aspects of the environment, these agents dynamically filter out the relevant ones and then pass them to their simulator to perform partial reasoning. Unlike existing approaches, our approach works with pixel-based inputs and it allows for interpreting the focal points of the agent. Our quantitative analyses show that the proposed approach allows for effective generalization in high-dimensional domains with raw observational inputs. We also perform ablation analyses to validate our design choices. Finally, we demonstrate through qualitative analyses that our approach actually allows for building agents that focus their reasoning on the relevant aspects of the environment.
2024-09-17
TMLR (accepted)
openreview.net
openreview.net