Related papers: Playing Mastermind with Wordle-like Feedback

The act of explaining across two parties is a feedback loop, where one provides information on what needs to be explained and the other provides an explanation relevant to this information. We apply a reinforcement learning framework which…

When presented with questions involving visual thinking, humans naturally switch reasoning modalities, often forming mental images or drawing visual aids. Large language models have shown promising results in arithmetic and symbolic…

Existing dense or paragraph video captioning approaches rely on holistic representations of videos, possibly coupled with learned object/action representations, to condition hierarchical language decoders. However, they fundamentally lack…

We present a model of pragmatic referring expression interpretation in a grounded communication task (identifying colors from descriptions) that draws upon predictions from two recurrent neural network classifiers, a speaker and a listener,…

Transformer models have demonstrated impressive capabilities when trained at scale, excelling at difficult cognitive tasks requiring complex reasoning and rational decision-making. In this paper, we explore the application of transformers…

An agent who interacts with a wide population of other agents needs to be aware that there may be variations in their understanding of the world. Furthermore, the machinery which they use to perceive may be inherently different, as is the…

This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making. Inspired by dual-process theory in cognitive science, the representation…

Written responses can provide a wealth of data in understanding student reasoning on a topic. Yet they are time- and labor-intensive to score, requiring many instructors to forego them except as limited parts of summative assessments at the…

The need for grounding in language understanding is an active research topic. Previous work has suggested that color perception and color language appear as a suitable test bed to empirically study the problem, given its cognitive…

Robots will eventually be part of every household. It is thus critical to enable algorithms to learn from and be guided by non-expert users. In this paper, we bring a human in the loop, and enable a human teacher to give feedback to a…

Analogical reasoning is a hallmark of human intelligence, enabling us to solve new problems by transferring knowledge from one situation to another. Yet, developing artificial intelligence systems capable of robust human-like analogical…

Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate plausible-looking…

The widespread adoption of large language models (LLMs) underscores the urgent need to ensure their fairness. However, LLMs frequently present dominant viewpoints while ignoring alternative perspectives from minority parties, resulting in…

Word embedding, specially with its recent developments, promises a quantification of the similarity between terms. However, it is not clear to which extent this similarity value can be genuinely meaningful and useful for subsequent tasks.…

This paper presents a mathematical method of playing the puzzle game Wordle. In Wordle, the player has six tries to guess a secret word. After each guess the player is told how their guess compares to the secret word. With the available…

Specifications are vital for ensuring program correctness, yet writing them manually remains challenging and time-intensive. Recent large language model (LLM)-based methods have shown successes in generating specifications such as…

This paper presents an innovative framework that integrates Large Language Models (LLMs) with an external Thinker module to enhance the reasoning capabilities of LLM-based agents. Unlike augmenting LLMs with prompt engineering, Thinker…

Formative feedback is central to effective learning, yet providing timely, individualised feedback at scale remains a persistent challenge. While recent work has explored the use of large language models (LLMs) to automate feedback, most…

In large language models (LLMs), code and reasoning reinforce each other: code offers an abstract, modular, and logic-driven structure that supports reasoning, while reasoning translates high-level goals into smaller, executable steps that…

Transparent machine learning is introduced as an alternative form of machine learning, where both the model and the learning system are represented in source code form. The goal of this project is to enable direct human understanding of…