AI & ML interests
computational linguistics, natural language processing
Recent Activity
View all activity
Papers
Forecasting Downstream Performance of LLMs With Proxy Metrics
Structured Distillation of Web Agent Capabilities Enables Generalization
Models and data from "Structured Distillation of Web Agent Capabilities Enables Generalization" (arXiv:2604.07776)
-
Structured Distillation of Web Agent Capabilities Enables Generalization
Paper • 2604.07776 • Published • 23 -
McGill-NLP/A3-Qwen3.5-9B
Image-Text-to-Text • 9B • Updated • 379 • 6 -
McGill-NLP/A3-Qwen3.5-4B
Image-Text-to-Text • 5B • Updated • 99 • 2 -
McGill-NLP/A3-Qwen3.5-2B
Image-Text-to-Text • 3B • Updated • 32 • 2
Pre-computed contextual text embeddings for interpreting LLM/VLM hidden states. Use with: pip install latentlens
Reformulating the RL of reasoning LLMs through Markovian Thinking paradigm.
-
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
Paper • 2504.08942 • Published • 29 -
McGill-NLP/agent-reward-bench
Viewer • Updated • 1.41k • 6.28k • 4 -
Agent Reward Bench Demo
💻5Explore agent trajectories and judgments in web benchmarks
-
Agent Reward Bench Leaderboard
🥇3Leaderboard for AgentRewardBench
-
McGill-NLP/LLM2Vec-Meta-Llama-32-3B-Instruct-mntp-supervised
Updated -
McGill-NLP/LLM2Vec-Meta-Llama-31-8B-Instruct-mntp-supervised
Sentence Similarity • Updated • 352 • 5 -
McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised
Sentence Similarity • Updated • 118k • 52 -
McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised
Sentence Similarity • Updated • 409 • 13
Repository: https://github.com/McGill-NLP/AURORA
mcgill-nlp.github.io/statcan-dialogue-dataset
-
The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents
Paper • 2304.01412 • Published • 2 -
McGill-NLP/statcan-dialogue-dataset
Preview • Updated • 4 • 7 -
McGill-NLP/dpr-statcan-conversation_encoder-title
Feature Extraction • 0.1B • Updated • 9 -
McGill-NLP/tapas-statcan-large-conversation_encoder-cell_tokens
Feature Extraction • Updated • 6
-
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval
Paper • 2104.08801 • Published • 1 -
McGill-NLP/mlquestions
Updated • 193 • 3 -
McGill-NLP/bart-qg-mlquestions-backtraining
Updated • 10 -
McGill-NLP/bart-qg-mlquestions-selftraining
Updated • 8
Best open African LLM
-
AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages
Paper • 2601.06395 • Published • 5 -
McGill-NLP/AfriqueQwen-14B
Text Generation • 15B • Updated • 2.28k • • 4 -
McGill-NLP/AfriqueQwen-8B
Text Generation • 8B • Updated • 1.56k • • 2 -
McGill-NLP/AfriqueQwen3.5-4B-50Langs
Text Generation • 5B • Updated • 206 • 5
Generative Embeddings from Large Language Models
INJONGO: A Multicultural Intent Detection and Slot-filling Dataset for 16 African Languages
-
McGill-NLP/AfroXLMR-large-76L-Injongo-intent
Text Classification • 0.6B • Updated • 5 -
McGill-NLP/AfroXLMR-large-76L-Injongo-slot
Token Classification • 0.6B • Updated • 26 -
McGill-NLP/gemma-2-9b-it-Injongo-intent
Text Generation • 9B • Updated • 5 -
McGill-NLP/gemma-2-9b-it-Injongo-slot
Text Generation • 9B • Updated • 5
Datasets used for the OLMo experiments in the "Not All Data are Unlearned Equally" paper https://arxiv.org/abs/2504.05058
Generate challenging synthetic data to evaluate LLMs
https://mcgill-nlp.github.io/weblinx
https://mcgill-nlp.github.io/weblinx
Best open African LLM
-
AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages
Paper • 2601.06395 • Published • 5 -
McGill-NLP/AfriqueQwen-14B
Text Generation • 15B • Updated • 2.28k • • 4 -
McGill-NLP/AfriqueQwen-8B
Text Generation • 8B • Updated • 1.56k • • 2 -
McGill-NLP/AfriqueQwen3.5-4B-50Langs
Text Generation • 5B • Updated • 206 • 5
Models and data from "Structured Distillation of Web Agent Capabilities Enables Generalization" (arXiv:2604.07776)
-
Structured Distillation of Web Agent Capabilities Enables Generalization
Paper • 2604.07776 • Published • 23 -
McGill-NLP/A3-Qwen3.5-9B
Image-Text-to-Text • 9B • Updated • 379 • 6 -
McGill-NLP/A3-Qwen3.5-4B
Image-Text-to-Text • 5B • Updated • 99 • 2 -
McGill-NLP/A3-Qwen3.5-2B
Image-Text-to-Text • 3B • Updated • 32 • 2
Generative Embeddings from Large Language Models
Pre-computed contextual text embeddings for interpreting LLM/VLM hidden states. Use with: pip install latentlens
Reformulating the RL of reasoning LLMs through Markovian Thinking paradigm.
INJONGO: A Multicultural Intent Detection and Slot-filling Dataset for 16 African Languages
-
McGill-NLP/AfroXLMR-large-76L-Injongo-intent
Text Classification • 0.6B • Updated • 5 -
McGill-NLP/AfroXLMR-large-76L-Injongo-slot
Token Classification • 0.6B • Updated • 26 -
McGill-NLP/gemma-2-9b-it-Injongo-intent
Text Generation • 9B • Updated • 5 -
McGill-NLP/gemma-2-9b-it-Injongo-slot
Text Generation • 9B • Updated • 5
Datasets used for the OLMo experiments in the "Not All Data are Unlearned Equally" paper https://arxiv.org/abs/2504.05058
-
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
Paper • 2504.08942 • Published • 29 -
McGill-NLP/agent-reward-bench
Viewer • Updated • 1.41k • 6.28k • 4 -
Agent Reward Bench Demo
💻5Explore agent trajectories and judgments in web benchmarks
-
Agent Reward Bench Leaderboard
🥇3Leaderboard for AgentRewardBench
Generate challenging synthetic data to evaluate LLMs
-
McGill-NLP/LLM2Vec-Meta-Llama-32-3B-Instruct-mntp-supervised
Updated -
McGill-NLP/LLM2Vec-Meta-Llama-31-8B-Instruct-mntp-supervised
Sentence Similarity • Updated • 352 • 5 -
McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised
Sentence Similarity • Updated • 118k • 52 -
McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp-supervised
Sentence Similarity • Updated • 409 • 13
https://mcgill-nlp.github.io/weblinx
Repository: https://github.com/McGill-NLP/AURORA
https://mcgill-nlp.github.io/weblinx
mcgill-nlp.github.io/statcan-dialogue-dataset
-
The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents
Paper • 2304.01412 • Published • 2 -
McGill-NLP/statcan-dialogue-dataset
Preview • Updated • 4 • 7 -
McGill-NLP/dpr-statcan-conversation_encoder-title
Feature Extraction • 0.1B • Updated • 9 -
McGill-NLP/tapas-statcan-large-conversation_encoder-cell_tokens
Feature Extraction • Updated • 6
-
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval
Paper • 2104.08801 • Published • 1 -
McGill-NLP/mlquestions
Updated • 193 • 3 -
McGill-NLP/bart-qg-mlquestions-backtraining
Updated • 10 -
McGill-NLP/bart-qg-mlquestions-selftraining
Updated • 8