Search Results for author:
Found 14 papers, 4 papers with code
RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs
Existing pretrained LLMs may generate summaries that are concise but lack the necessary context for downstream tasks, hindering their utility in personalization systems.
A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models
Our contributions include a multifactorial framework for human assessment of LLM-generated answers for biases, and EquityMedQA, a collection of seven datasets enriched for adversarial queries.
Augmentations vs Algorithms: What Works in Self-Supervised Learning
We study the relative effects of data augmentations, pretraining algorithms, and model architectures in Self-Supervised Learning (SSL).
User-LLM: Efficient LLM Contextualization with User Embeddings
We integrate these user embeddings with LLMs through cross-attention, enabling LLMs to dynamically adapt their responses based on the context of a user's past actions and preferences.
ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
Answering complex natural language questions often necessitates multi-step reasoning and integrating external information.
Ranked #1 on
Question Answering
on Bamboogle
Towards Accurate Differential Diagnosis with Large Language Models
Comparing the two assisted study arms, the DDx quality score was higher for clinicians assisted by our LLM (top-10 accuracy 51. 7%) compared to clinicians without its assistance (36. 1%) (McNemar's Test: 45. 7, p < 0. 01) and clinicians with search (44. 4%) (4. 75, p = 0. 03).
Universal Self-Consistency for Large Language Model Generation
Self-consistency with chain-of-thought prompting (CoT) has demonstrated remarkable performance gains on various challenging tasks, by utilizing multiple reasoning paths sampled from large language models (LLMs).
RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but gathering high-quality preference labels is expensive.
Towards Generalist Biomedical AI
While considerable work is needed to validate these models in real-world use cases, our results represent a milestone towards the development of generalist biomedical AI systems.
Towards Expert-Level Medical Question Answering with Large Language Models
Large language models (LLMs) have catalyzed significant progress in medical question answering; Med-PaLM was the first model to exceed a "passing" score in US Medical Licensing Examination (USMLE) style questions with a score of 67. 2% on the MedQA dataset.
A Unified Approach to Entity-Centric Context Tracking in Social Conversations
Second, we open-source a neural network architecture for context tracking.
Learning Federated Representations and Recommendations with Limited Negatives
Deep retrieval models are widely used for learning entity representations and recommendations.
Federated Reconstruction: Partially Local Federated Learning
We also describe the successful deployment of this approach at scale for federated collaborative filtering in a mobile keyboard application.
Toward Interpretability of Dual-Encoder Models for Dialogue Response Suggestions
To improve the interpretability in the dual encoder models, we design a novel regularization loss to minimize the mutual information between unimportant words and desired labels, in addition to the original attention method, so that important words are emphasized while unimportant words are de-emphasized.
