Search Results for author:
Found 15 papers, 12 papers with code
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
We find that such backdoor behavior can be made persistent, so that it is not removed by standard safety training techniques, including supervised fine-tuning, reinforcement learning, and adversarial training (eliciting unsafe behavior and then training to remove it).
Characterizing tradeoffs between teaching via language and demonstrations in multi-agent systems
Humans teach others about the world through language and demonstration.
Learning to Compress Prompts with Gist Tokens
Prompting is the primary way to utilize the multitask capabilities of language models (LMs), but prompts occupy valuable space in the input context window, and repeatedly encoding the same prompt is computationally inefficient.
Improving Policy Learning via Language Dynamics Distillation
Recent work has shown that augmenting environments with language descriptions improves policy learning.
Active Learning Helps Pretrained Models Learn the Intended Task
Models can fail in unpredictable ways during deployment due to task ambiguity, when multiple behaviors are consistent with the provided training data.
STaR: Bootstrapping Reasoning With Reasoning
We show that STaR significantly improves performance on multiple datasets compared to a model fine-tuned to directly predict final answers, and performs comparably to fine-tuning a 30$\times$ larger state-of-the-art language model on CommensenseQA.
Ranked #17 on
Common Sense Reasoning
on CommonsenseQA
Improving Intrinsic Exploration with Language Abstractions
Reinforcement learning (RL) agents are particularly hard to train when rewards are sparse.
Calibrate your listeners! Robust communication-based training for pragmatic speakers
We propose a method that uses a population of neural listeners to regularize speaker training.
Pretrained models are active learners
An important barrier to the safe deployment of machine learning systems is the risk of \emph{task ambiguity}, where multiple behaviors are consistent with the provided examples.
Emergent Communication of Generalizations
To build agents that can collaborate effectively with others, recent research has trained artificial agents to communicate with each other in Lewis-style referential games.
Compositional Explanations of Neurons
We describe a procedure for explaining neurons in deep representations by identifying compositional logical concepts that closely approximate neuron behavior.
Learning to refer informatively by amortizing pragmatic reasoning
A hallmark of human language is the ability to effectively and efficiently convey contextually relevant information.
Shaping Visual Representations with Language for Few-shot Classification
By describing the features and abstractions of our world, language is a crucial tool for human learning and a promising source of supervision for machine learning models.
Learning Outside the Box: Discourse-level Features Improve Metaphor Identification
Most current approaches to metaphor identification use restricted linguistic contexts, e. g. by considering only a verb's arguments or the sentence containing a phrase.
Evaluating Hierarchies of Verb Argument Structure with Hierarchical Clustering
Verbs can only be used with a few specific arrangements of their arguments (syntactic frames).
