Search Results for author:
Found 9 papers, 6 papers with code
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
Developing such algorithms requires tasks that can gauge progress on algorithm design, provide accessible and reproducible evaluations for multi-turn interactions, and cover a range of task properties and challenges in improving reinforcement learning algorithms.
The False Promise of Imitating Proprietary LLMs
This approach looks to cheaply imitate the proprietary model's capabilities using a weaker open-source model.
Learning by Distilling Context
We show that context distillation is a general method to train language models, and it can effectively internalize 3 types of training signals.
Offline RL for Natural Language Generation with Implicit Language Q Learning
Large language models distill broad knowledge from text corpora.
Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQL
We introduce APEL, a framework in which non-programmers select among candidate programs generated by a seed semantic parser (e. g., Codex).
Context-Aware Language Modeling for Goal-Oriented Dialogue Systems
Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control.
Describing Differences between Text Distributions with Natural Language
We then re-rank the descriptions by checking how often they hold on a larger set of samples with a learned verifier.
Approximating How Single Head Attention Learns
Our approximation explains why models sometimes attend to salient words, and inspires a toy example where a multi-head attention model can overcome the above hard training distribution by improving learning dynamics rather than expressiveness.
Understanding Attention Training via Output Relevance
If we ablate attention by fixing it to uniform, the output relevance still correlates with the attention of a normally trained model; but if we instead ablate output relevance, attention cannot be learned.
