Search Results for author:
Found 19 papers, 10 papers with code
Scaling up the think-aloud method
The think-aloud method, where participants voice their thoughts as they solve a task, is a valuable source of rich data about human reasoning processes.
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
In systematic experimentation with controlled behavioral datasets, we find that priming Llama with examples containing these reasoning behaviors enables substantial improvements during RL, matching or exceeding Qwen's performance.
Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models
However, existing open math datasets either contain a small collection of high-quality, human-written problems or a large corpus of machine-generated problems of uncertain quality, forcing researchers to choose between quality and quantity.
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though
We propose a novel framework, Meta Chain-of-Thought (Meta-CoT), which extends traditional Chain-of-Thought (CoT) by explicitly modeling the underlying reasoning required to arrive at a particular CoT.
BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery
To quantitatively evaluate a scientific agent's ability to collect informative experimental data, we compute the expected information gain (EIG), an information-theoretic quantity which measures how much an experiment reduces uncertainty about the parameters of a generative model.
Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models
Further, we emphasize the existence of Quality-Diversity trade-offs in training data and the downstream effects on model performance.
Human-like Affective Cognition in Foundation Models
Understanding emotions is fundamental to human interaction and experience.
Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models
We demonstrate that our metric can capture important variations in populations that traditional metrics, like differences in accuracy, fail to capture.
Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels
On single-turn dialogue and summarization, a SAMI-trained mistral-7b outperforms the initial pretrained model, with win rates between 66% and 77%.
Procedural Dilemma Generation for Evaluating Moral Reasoning in Humans and Language Models
We collected moral permissibility and intention judgments from human participants for a subset of our items and compared these judgments to those from two language models (GPT-4 and Claude-2) across eight conditions.
Stream of Search (SoS): Learning to Search in Language
In this paper, we show how language models can be taught to search by representing the process of search in language, as a flattened string -- a stream of search (SoS).
Social Contract AI: Aligning AI Assistants with Implicit Group Norms
We explore the idea of aligning an AI assistant by inverting a model of users' (unknown) preferences from observed interactions.
A Fourier Neural Operator Approach for Modelling Exciton-Polariton Condensate Systems
A plethora of next-generation all-optical devices based on exciton-polaritons have been proposed in latest years, including prototypes of transistors, switches, analogue quantum simulators and others.
Understanding Social Reasoning in Language Models with Language Models
Using our framework, we create a new social reasoning benchmark (BigToM) for LLMs which consists of 25 controls and 5, 000 model-written evaluations.
Certified Deductive Reasoning with Language Models
In experiments on PrOntoQA, ProofWriter and Syllogism Validity datasets, \textsc{LogicGuide} significantly improves the performance of GPT-3, GPT-3. 5 Turbo and LLaMA (accuracy gains up to 35\%), while drastically reducing \emph{content effects} -- the interference between unwanted prior assumptions and reasoning, which humans and language models suffer from.
Strategic Reasoning with Language Models
Existing approaches to solving strategic games rely on extensive training, yielding strategies that do not generalize to new scenarios or games without retraining.
Eliciting Compatible Demonstrations for Multi-Human Imitation Learning
Imitation learning from human-provided demonstrations is a strong approach for learning policies for robot manipulation.
Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others
To achieve human-like common sense about everyday life, machine learning systems must understand and reason about the goals, preferences, and actions of other agents in the environment.
Mutual exclusivity as a challenge for deep neural networks
Strong inductive biases allow children to learn in fast and adaptable ways.
