Related papers: From Zero to Hero: Convincing with Extremely Compl…
Texts present coherent stories that have a particular theme or overall setting, for example science fiction or western. In this paper, we present a text generation method called {\it rewriting} that edits existing human-authored narratives…
We propose Text2Math, a model for semantically parsing text into math expressions. The model can be used to solve different math related problems including arithmetic word problems and equation parsing problems. Unlike previous approaches,…
[Taken from the "README" in the book] My goal with this book is to provide some kind of bridge for mathematics between the high-school-level and college-level for physics students. From my perspective, our job as physicists is to observe…
Verifying mathematical proofs is difficult, but can be automated with the assistance of a computer. Autoformalization is the task of automatically translating natural language mathematics into a formal language that can be verified by a…
We aim to improve the reasoning capabilities of language models via reinforcement learning (RL). Recent RL post-trained models like DeepSeek-R1 have demonstrated reasoning abilities on mathematical and coding tasks. However, prior studies…
Multi-hop question answering (QA) is a challenging task requiring QA systems to perform complex reasoning over multiple documents and provide supporting facts together with the exact answer. Existing works tend to utilize graph-based…
As large language models (LLMs) advance their mathematical capabilities toward the IMO level, the scarcity of challenging, high-quality problems for training and evaluation has become a significant bottleneck. Simultaneously, recent code…
Large Language Model (LLMs) can be used to write or modify documents, presenting a challenge for understanding the intent behind their use. For example, benign uses may involve using LLM on a human-written document to improve its grammar or…
Humor is an important social phenomenon, serving complex social and psychological functions. However, despite being studied for millennia humor is computationally not well understood, often considered an AI-complete problem. In this work,…
Math is the backbone of any field. Still its a night mare for many. Recent survey proves that many students become dropouts from their higher education due to math courses. ICT is an enchanted word in the contemporary educational…
In response to the increasing use of interactive artificial intelligence, the demand for the capacity to handle complex questions has increased. Multi-hop question generation aims to generate complex questions that requires multi-step…
Humor is an essential human trait. Efforts to understand humor have called out links between humor and the foundations of cognition, as well as the importance of humor in social engagement. As such, it is a promising and important subject…
This paper presents our winning submission to the AI Mathematical Olympiad - Progress Prize 2 (AIMO-2) competition. Our recipe for building state-of-the-art mathematical reasoning models relies on three key pillars. First, we create a…
The example of the calculus is used to explain how simple, practical math was made enormously complex by imposing on it the Western religiously-colored notion of mathematics as "perfect". We describe a pedagogical experiment to make math…
This paper presents HerO 2, Team HUMANE's system for the AVeriTeC shared task at the FEVER-25 workshop. HerO 2 is an enhanced version of HerO, the best-performing open-source model from the previous year's challenge. It improves evidence…
While generalization over tasks from easy to hard is crucial to profile language models (LLMs), the datasets with fine-grained difficulty annotations for each problem across a broad range of complexity are still blank. Aiming to address…
"Mathematicians, like physicists, are pushed by a strong fascination. Research in mathematics is hard, it is intellectually painful even if it is rewarding, and you would not do it without some strong urge." [D. Ruelle]. We shall give some…
Replication of scientific experiments is critical to the advance of science. Unfortunately, the discipline of Computer Science has never treated replication seriously, even though computers are very good at doing the same thing over and…
Training deep neural networks may be challenging in real world data. Using models as black-boxes, even with transfer learning, can result in poor generalization or inconclusive results when it comes to small datasets or specific…
An important recurring pattern in scientific breakthroughs is a two-stage process: an initial phase of undirected experimentation that yields an unexpected finding, followed by a retrospective phase that explains why the finding works and…