Search Results for author:
Found 19 papers, 6 papers with code
Self-Consistency Preference Optimization
Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area.
To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning
In this paper, we propose To the Globe (TTG), a real-time demo system that takes natural language requests from users, translates it to symbolic form via a fine-tuned Large Language Model, and produces optimal travel itineraries with Mixed Integer Linear Programming solvers.
Self-Taught Evaluators
Model-based evaluation is at the heart of successful model development -- as a reward model for training, and as a replacement for human evaluation.
PathFinder: Guided Search over Multi-Step Reasoning Paths
Using constrained reasoning, PathFinder integrates novel quality constraints, pruning, and exploration methods to enhance the efficiency and the quality of generation.
DOMINO: A Dual-System for Multi-step Visual Language Reasoning
By fine-tuning the System-2 module (LLaMA-2 70B) on only a small amount of data on multi-step reasoning, the accuracy of our method is further improved and surpasses the best fully-supervised end-to-end approach by 5. 7% and a pipeline approach with FlanPaLM (540B) by 7. 5% on a challenging dataset with human-authored questions.
Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
It is also a general-purpose model that can do both text-to-image and image-to-text generation, allowing us to introduce self-contained contrastive decoding methods that produce high-quality outputs.
Ranked #2 on
Text-to-Image Generation
on COCO
Shepherd: A Critic for Language Model Generation
As large language models improve, there is increasing interest in techniques that leverage these models' capabilities to refine their own outputs.
Scaling Speech Technology to 1,000+ Languages
Expanding the language coverage of speech technology has the potential to improve access to information for many more people.
Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture and Single-Source Speech
Self-supervised learning leverages unlabeled data effectively, improving label efficiency and generalization to domains without labeled data.
ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning
Large language models show improved downstream task performance when prompted to generate step-by-step reasoning to justify their final answers.
Language models of protein sequences at the scale of evolution enable accurate structure prediction
We find that as models are scaled they learn information enabling the prediction of the three-dimensional structure of a protein at the resolution of individual atoms.
Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue Systems
Our proposed method allows a single transformer model to directly walk on a large-scale knowledge graph to generate responses.
Logical Reasoning for Task Oriented Dialogue Systems
We observe that transformer based models such as UnifiedQA-T5 can be fine-tuned to perform logical reasoning (such as numerical and categorical attributes' comparison) over attributes that been seen in training time (e. g., accuracy of 90\%+ for comparison of smaller than $k_{\max}$=5 values over heldout test dataset).
Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems
Finally, we evaluate our system using a typical movie ticket booking task and show that the dialogue simulator is an essential component of the system that leads to over $50\%$ improvement in turn-level action signature prediction accuracy.
Dialog Simulation with Realistic Variations for Training Goal-Oriented Conversational Systems
Our approach includes a novel goal-sampling technique for sampling plausible user goals and a dialog simulation technique that uses heuristic interplay between the user and the system (Alexa), where the user tries to achieve the sampled goal.
Data Augmentation for Training Dialog Models Robust to Speech Recognition Errors
Speech-based virtual assistants, such as Amazon Alexa, Google assistant, and Apple Siri, typically convert users' audio signals to text data through automatic speech recognition (ASR) and feed the text to downstream dialog models for natural language understanding and response generation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Towards Personalized Dialog Policies for Conversational Skill Discovery
Many businesses and consumers are extending the capabilities of voice-based services such as Amazon Alexa, Google Home, Microsoft Cortana, and Apple Siri to create custom voice experiences (also known as skills).
Investigation of Error Simulation Techniques for Learning Dialog Policies for Conversational Error Recovery
Training dialog policies for speech-based virtual assistants requires a plethora of conversational data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Learning Robust Dialog Policies in Noisy Environments
In this paper, we focus on learning robust dialog policies to recover from these errors.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
