Alessandro Sordoni

43 papers · 2015–2026 · 11 conferences · across top CS/AI conferences

Achievements

+15 more ↓

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (11) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (10)

🌉 Interdisciplinary Bridge 🏃 Academic Marathon (10) 🧭 Keyword Pioneer 🤝 Dynamic Duo (10) 👑 Triple Crown 🏆 Grand Slam 🌱 Topic Pioneer 🧬 Topic Evolution 🔥 Unstoppable (11) 🚀 Conference Pioneer ❓ The Questioner ⚡ Prolific Year (6) 🗃️ Keyword Collector (168) 💎 Century Club (42) 📈 Trend Setter

Conferences

NIPS (9) EMNLP (7) ACL (6) ICML (6) ICLR (4) NAACL (4) EACL (3) AAAI (1) COLING (1) CONLL (1) IJCNLP (1)

Top co-authors

Aaron Courville (10) Adam Trischler (8) Yikang Shen (6) Shawn Tan (6) Yoshua Bengio (6) Nicolas Le Roux (5) Siva Reddy (4) Zhouhan Lin (4) Philip Bachman (4) Arian Hosseini (4)

Keywords

large language model (4) language model (4) few-shot learning (4) recurrent neural network (3) tree structure (3) variational inference (3) pre-trained language model (2) masked language modeling (2) dependency parsing (2) representation learning (2) out-of-distribution generalization (2) question answering (2) sequence labeling (2) attention mechanism (2) language modeling (2) information theory (2) text classification (2) reinforcement learning (2) communicative efficiency (2) language acquisition (2)

Papers

MedRiskEval: Medical Risk Evaluation Benchmark of Language Models, On the Importance of User Perspectives in Healthcare Settings EACL 2026 A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment ACL 2025 VinePPO: Refining Credit Assignment in RL Training of LLMs ICML 2025 Efficient Adversarial Training in LLMs with Continuous Attacks NIPS 2024 Towards Modular LLMs by Building and Reusing a Library of LoRAs ICML 2024 Efficient Reinforcement Learning by Discovering Neural Pathways NIPS 2024 Improving Context-Aware Preference Modeling for Language Models NIPS 2024 Joint Prompt Optimization of Stacked LLMs using Variational Inference NIPS 2023 Multi-Head Adapter Routing for Cross-Task Generalization NIPS 2023 Combining Parameter-efficient Modules for Task-level Generalisation EACL 2023 Learning to Dequantise with Truncated Flows ICLR 2022 Better Language Model with Hypernym Class Prediction ACL 2022 Unsupervised Dependency Graph Network ACL 2022 Measuring Morphological Fusion Using Partial Information Decomposition COLING 2022 Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge NAACL 2022 On the Compositional Generalization Gap of In-Context Learning EMNLP 2022 Evaluating Distributional Distortion in Neural Language Modeling ICLR 2022 Understanding by Understanding Not: Modeling Negation in Language Models NAACL 2021 Increasing Robustness to Spurious Correlations using Forgettable Examples EACL 2021 Decomposed Mutual Information Estimation for Contrastive Representation Learning ICML 2021 Self-training with Few-shot Rationalization EMNLP 2021 The Emergence of the Shape Bias Results from Communicative Efficiency EMNLP 2021 Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle NAACL 2021 Quantum-inspired Neural Network for Conversational Emotion Recognition AAAI 2021 The Emergence of the Shape Bias Results from Communicative Efficiency CONLL 2021 Linguistic Dependencies and Statistical Dependence EMNLP 2021 Exploring and Predicting Transferability across NLP Tasks EMNLP 2020 Recursive Top-Down Production for Sentence Generation with Latent Trees EMNLP 2020 Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks ICLR 2019 Metalearned Neural Memory NIPS 2019 Ordered Memory NIPS 2019 Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data ICML 2018 Towards Text Generation with Adversarially Learned Neural Outlines NIPS 2018 Straight to the Tree: Constituency Parsing with Neural Syntactic Distance ACL 2018 Learning Hierarchical Structures On-The-Fly with a Recurrent-Recursive Model for Sequences ACL 2018 Twin Networks: Matching the Future for Sequence Generation ICLR 2018 Focused Hierarchical RNNs for Conditional Sequence Processing ICML 2018 Z-Forcing: Training Stochastic Recurrent Networks NIPS 2017 Learning Algorithms for Active Learning ICML 2017 Natural Language Comprehension with the EpiReader EMNLP 2016 deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets IJCNLP 2015 A Neural Network Approach to Context-Sensitive Generation of Conversational Responses NAACL 2015 deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets ACL 2015