Search Results for author:
Found 10 papers, 3 papers with code
Progressive Safeguards for Safe and Model-Agnostic Reinforcement Learning
Our framework is inspired by how parents safeguard their children across a progression of increasingly riskier tasks, imparting a sense of safety that is carried over from task to task.
Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" Cycle
Recent innovations in language model training have demonstrated that it is possible to create highly performant models that are small enough to run on a smartphone.
Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning
Reinforcement learning with human feedback (RLHF), as a widely adopted approach in current large language model pipelines, is \textit{bottlenecked by the size of human preference data}.
Self-Exploring Language Models: Active Preference Elicitation for Online Alignment
Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions.
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
We introduce phi-3-mini, a 3. 8 billion parameter language model trained on 3. 3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3. 5 (e. g., phi-3-mini achieves 69% on MMLU and 8. 38 on MT-bench), despite being small enough to be deployed on a phone.
Ranked #5 on
MMR total
on MRR-Benchmark
(using extra training data)
Language Models can be Logical Solvers
Despite their impressive performance, any parsing errors will inevitably result in the failure of the execution of the external logical solver and no answer to the logical questions.
ALLURE: Auditing and Improving LLM-based Evaluation of Text using Iterative In-Context-Learning
From grading papers to summarizing medical documents, large language models (LLMs) are evermore used for evaluation of text generated by humans and AI alike.
Fine-Tuning Language Models with Advantage-Induced Policy Alignment
Reinforcement learning from human feedback (RLHF) has emerged as a reliable approach to aligning large language models (LLMs) to human preferences.
Randomized Policy Learning for Continuous State and Action MDPs
The key to success has been the use of deep neural networks used to approximate the policy and value function.
Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes
Model-free reinforcement learning is known to be memory and computation efficient and more amendable to large scale problems.
