English
Related papers

Related papers: Math Takes Two: A test for emergent mathematical r…

200 papers

Recent Large Language Models (LLMs) have reported high accuracy on reasoning benchmarks. However, it is still unclear whether the observed results arise from true reasoning or from statistical recall of the training set. Inspired by the…

Computation and Language · Computer Science 2025-06-19 Xinnuo Xu , Rachel Lawrence , Kshitij Dubey , Atharva Pandey , Risa Ueno , Fabian Falck , Aditya V. Nori , Rahul Sharma , Amit Sharma , Javier Gonzalez

Artificial agents that learn to communicate in order to accomplish a given task acquire communication protocols that are typically opaque to a human. A large body of work has attempted to evaluate the emergent communication via various…

Artificial Intelligence · Computer Science 2024-03-25 Boaz Carmeli , Yonatan Belinkov , Ron Meir

Humans use signs, e.g., sentences in a spoken language, for communication and thought. Hence, symbol systems like language are crucial for our communication with other agents and adaptation to our real-world environment. The symbol systems…

Large language models (LLMs) can perform reasoning computations both internally within their latent space and externally by generating explicit token sequences like chains of thought. Significant progress in enhancing reasoning abilities…

Computation and Language · Computer Science 2025-04-16 Thilo Hagendorff , Sarah Fabi

We propose a benchmark to assess the capability of large language models to reason with conventional metaphors. Our benchmark combines the previously isolated topics of metaphor detection and commonsense reasoning into a single task that…

Computation and Language · Computer Science 2022-10-17 Iulia-Maria Comsa , Julian Martin Eisenschlos , Srini Narayanan

The rapid rise of Large Language Models (LLMs) and Large Reasoning Models (LRMs) has been accompanied by an equally rapid increase of benchmarks used to assess them. However, due to both improved model competence resulting from scaling and…

Computation and Language · Computer Science 2025-11-04 İbrahim Ethem Deveci , Duygu Ataman

Large language models (LLMs) are a promising venue for natural language understanding and generation. However, current LLMs are far from reliable: they are prone to generating non-factual information and, more crucially, to contradicting…

Computation and Language · Computer Science 2024-09-24 Diego Calanzone , Stefano Teso , Antonio Vergari

Trained on vast corpora of human language, language models demonstrate emergent human-like reasoning abilities. Yet they are still far from true intelligence, which opens up intriguing opportunities to explore the parallels of humans and…

Computation and Language · Computer Science 2024-11-05 Tengxiao Liu , Qipeng Guo , Xiangkun Hu , Cheng Jiayang , Yue Zhang , Xipeng Qiu , Zheng Zhang

It has become a common pattern in our field: One group introduces a language task, exemplified by a dataset, which they argue is challenging enough to serve as a benchmark. They also provide a baseline model for it, which then soon is…

Computation and Language · Computer Science 2020-07-10 David Schlangen

AI for Mathematics (AI4Math) has emerged as a distinct field that leverages machine learning to navigate mathematical landscapes historically intractable for early symbolic systems. While mid-20th-century symbolic approaches successfully…

History and Overview · Mathematics 2026-05-05 Haocheng Ju , Bin Dong

The cognitive mechanism by which Large Language Models (LLMs) solve mathematical problems remains a widely debated and unresolved issue. Currently, there is little interpretable experimental evidence that connects LLMs' problem-solving with…

Artificial Intelligence · Computer Science 2025-09-23 Wei Xie , Shuoyoucheng Ma , Zhenhua Wang , Enze Wang , Kai Chen , Xiaobing Sun , Baosheng Wang

Text-to-image generative models are capable of producing high-quality images that often faithfully depict concepts described using natural language. In this work, we comprehensively evaluate a range of text-to-image models on numerical…

Machine Learning · Computer Science 2025-02-07 Ivana Kajić , Olivia Wiles , Isabela Albuquerque , Matthias Bauer , Su Wang , Jordi Pont-Tuset , Aida Nematzadeh

Achieving machine intelligence requires a smooth integration of perception and reasoning, yet models developed to date tend to specialize in one or the other; sophisticated manipulation of symbols acquired from rich perceptual spaces has so…

Machine Learning · Computer Science 2018-09-14 Eric Crawford , Guillaume Rabusseau , Joelle Pineau

Mathematical problem solving remains a challenging test of reasoning for large language and multimodal models, yet existing benchmarks are limited in size, language coverage, and task diversity. We introduce MathNet, a high-quality,…

Artificial Intelligence · Computer Science 2026-04-21 Shaden Alshammari , Kevin Wen , Abrar Zainal , Mark Hamilton , Navid Safaei , Sultan Albarakati , William T. Freeman , Antonio Torralba

The human ability to flexibly reason using analogies with domain-general content depends on mechanisms for identifying relations between concepts, and for mapping concepts and their relations across analogs. Building on a recent model of…

Artificial Intelligence · Computer Science 2021-10-06 Hongjing Lu , Nicholas Ichien , Keith J. Holyoak

Despite great performance on Olympiad-level reasoning problems, frontier large language models can still struggle on high school math when presented with novel problems outside standard benchmarks. Going beyond final accuracy, we propose a…

Computation and Language · Computer Science 2025-04-10 Atharva Pandey , Kshitij Dubey , Rahul Sharma , Amit Sharma

Large Language Models (LLMs) have succeeded remarkably in various natural language processing (NLP) tasks, yet their reasoning capabilities remain a fundamental challenge. While LLMs exhibit impressive fluency and factual recall, their…

Computation and Language · Computer Science 2025-05-29 Avinash Patil , Aryan Jadon

Advances in large language models (LLMs) have spurred research into enhancing their reasoning capabilities, particularly in math-rich STEM (Science, Technology, Engineering, and Mathematics) documents. While LLMs can generate equations or…

Computation and Language · Computer Science 2025-06-03 Jiaru Zou , Qing Wang , Pratyush Thakur , Nickvash Kani

While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, particularly under uncertainty, given ill-posed or ambiguous queries. We introduce statistically…

Artificial Intelligence · Computer Science 2026-02-17 Yangxinyu Xie , Tao Wang , Soham Mallick , Yan Sun , Georgy Noarov , Mengxin Yu , Tanwi Mallick , Weijie J. Su , Edgar Dobriban

Existing benchmarks for conversational AI agents simulate single-control environments, where only the AI agent can use tools to interact with the world, while the user remains a passive information provider. This differs from real-world…

Artificial Intelligence · Computer Science 2025-06-10 Victor Barres , Honghua Dong , Soham Ray , Xujie Si , Karthik Narasimhan