Search Results for author:
Found 10 papers, 7 papers with code
Language Model Inversion
We consider the problem of language model inversion and show that next-token probabilities contain a surprising amount of information about the preceding text.
Asking More Informative Questions for Grounded Retrieval
When a model is trying to gather information in an interactive setting, it benefits from asking informative questions.
Symbolic Planning and Code Generation for Grounded Dialogue
Large language models (LLMs) excel at processing and generating both text and code.
Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations
Instead of using direct supervision, this work proposes an approach for abductive commonsense reasoning that exploits the fact that only a subset of explanations is correct for a given context.
HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision
Explainable multi-hop question answering (QA) not only predicts answers but also identifies rationales, i. e. subsets of input sentences used to derive the answers.
Teal: Learning-Accelerated Optimization of WAN Traffic Engineering
The rapid expansion of global cloud wide-area networks (WANs) has posed a challenge for commercial optimization engines to efficiently solve network traffic engineering (TE) problems at scale.
Multi-agent Reinforcement Learning
Reinforcement Learning (RL)
Unsupervised Text Deidentification
We propose an unsupervised deidentification method that masks words that leak personally-identifying information.
Low-Rank Constraints for Fast Inference in Structured Models
This work demonstrates a simple approach to reduce the computational and memory complexity of a large class of structured models.
Reference-Centric Models for Grounded Collaborative Dialogue
We present a grounded neural dialogue model that successfully collaborates with people in a partially-observable reference game.
Scaling Hidden Markov Language Models
The hidden Markov model (HMM) is a fundamental tool for sequence modeling that cleanly separates the hidden state from the emission structure.
