相关论文: Playing Mastermind with Wordle-like Feedback

In the absence of abundant reliable annotations for challenging tasks and contexts, how can we expand the frontier of LLM capabilities with potentially wrong answers? We focus on two research questions: (1) Can LLMs generate reliable…

The ability to reason is one of the most fundamental capabilities of large language models (LLMs), enabling a wide range of downstream tasks through sophisticated problem-solving. A critical aspect of this is code reasoning, which involves…

Riddles are concise linguistic puzzles that describe an object or idea through indirect, figurative, or playful clues. They are a longstanding form of creative expression, requiring the solver to interpret hints, recognize patterns, and…

In machine learning algorithm design, there exists a trade-off between the interpretability and performance of the algorithm. In general, algorithms which are simpler and easier for humans to comprehend tend to show worse performance than…

We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…

Humans reason with concepts and metaconcepts: we recognize red and green from visual input; we also understand that they describe the same property of objects (i.e., the color). In this paper, we propose the visual concept-metaconcept…

The success of language models has inspired the NLP community to attend to tasks that require implicit and complex reasoning, relying on human-like commonsense mechanisms. While such vertical thinking tasks have been relatively popular,…

It is often difficult to hand-specify what the correct reward function is for a task, so researchers have instead aimed to learn reward functions from human behavior or feedback. The types of behavior interpreted as evidence of the reward…

The interplay between cognition and gaming, notably through educational games enhancing cognitive skills, has garnered significant attention in recent years. This research introduces the CogSimulator, a novel algorithm for simulating user…

When language models answer open-ended problems, they implicitly make hidden decisions that shape their outputs, leaving users with uncontextualized answers rather than a working map of the problem; drawing on multiverse analysis from…

We consider communication when there is no agreement about symbols and meanings. We treat it within the framework of reinforcement learning. We apply different reinforcement learning models in our studies and simplify the problem as much as…

The AB game is a two-player game, where the codemaker has to choose a secret code and the codebreaker has to guess it in as few questions as possible. It is a variant of the famous Mastermind game, with the only difference that all pegs in…

The Common Model of Cognition (CMC) provides an abstract characterization of the structure and processing required by a cognitive architecture for human-like minds. We propose a unified approach to integrating metacognition within the CMC.…

Cryptic crossword clues are challenging cognitive tasks, for which new test sets are released on a daily basis by multiple international newspapers. Each cryptic clue contains both the definition of the answer to be placed in the crossword…

Humans tend to learn complex abstract concepts faster if examples are presented in a structured manner. For instance, when learning how to play a board game, usually one of the first concepts learned is how the game ends, i.e. the actions…

This paper offers a new perspective on the limits of machine learning: the ceiling on progress is set not by model size or algorithm choice but by the information structure of the task itself. Code generation has progressed more reliably…

We suggest a new color distance based on two observations. First, perceptual color differences were designed to be used to compare very similar colors. They do not capture human perception for medium and large color differences well.…

Deep networks have shown impressive performance in the image restoration tasks, such as image colorization. However, we find that previous approaches rely on the digital representation from single color model with a specific mapping…

A compelling approach to complex question answering is to convert the question to a sequence of actions, which can then be executed on the knowledge base to yield the answer, aka the programmer-interpreter approach. Use similar training…

While Large language models (LLMs) have the capability to iteratively reflect on their own outputs, recent studies have observed their struggles with knowledge-rich problems without access to external resources. In addition to the…