research
∙
09/21/2023
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
We expose a surprising failure of generalization in auto-regressive larg...
share
research
∙
09/01/2023
Taken out of context: On measuring situational awareness in LLMs
We aim to better understand the emergence of `situational awareness' in ...
research
∙
07/27/2023
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback (RLHF) is a technique for tra...
research
∙
06/15/2023
Inverse Scaling: When Bigger Isn't Better
Work on scaling laws has found that large language models (LMs) show pre...
research
∙
03/28/2023
Training Language Models with Language Feedback at Scale
Pretrained language models often generate outputs that are not in line w...
research
∙
03/28/2023
Improving Code Generation by Training with Natural Language Feedback
The potential for pre-trained large language models (LLMs) to use natura...
research
∙
03/08/2023
Models of symbol emergence in communication: a conceptual review and a guide for avoiding local minima
Computational simulations are a popular method for testing hypotheses ab...
research
∙
02/16/2023
Pretraining Language Models with Human Preferences
Language models (LMs) are pretrained to imitate internet text, including...
research
∙
02/16/2023
Aligning Language Models with Preferences through f-divergence Minimization
Aligning language models with preferences can be posed as approximating ...
research
∙
06/01/2022
On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting
The availability of large pre-trained models is changing the landscape o...
research
∙
05/23/2022
RL with KL penalties is better viewed as Bayesian inference
Reinforcement learning (RL) is frequently employed in fine-tuning large ...
research
∙
12/01/2021
Controlling Conditional Language Models with Distributional Policy Gradients
Machine learning is shifting towards general-purpose pretrained generati...
research
∙
11/11/2021
Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
Communication is compositional if complex signals can be represented as ...
research
∙
06/09/2021
Energy-Based Models for Code Generation under Compilability Constraints
Neural language models can be successfully trained on source code, leadi...
research
∙
10/28/2020
Measuring non-trivial compositionality in emergent communication
Compositionality is an important explanatory target in emergent communic...
research
∙
10/04/2019
Developmentally motivated emergence of compositional communication via template transfer
This paper explores a novel approach to achieving emergent compositional...
research
∙
06/17/2019
Exploiting Unsupervised Pre-training and Automated Feature Engineering for Low-resource Hate Speech Detection in Polish
This paper presents our contribution to PolEval 2019 Task 6: Hate speech...
research
∙
11/03/2017