Related papers: ProofWriter: Generating Implications, Proofs, and …
The ability to reason with natural language is a fundamental prerequisite for many NLP tasks such as information extraction, machine translation and question answering. To quantify this ability, systems are commonly tested whether they can…
Large language models (LLMs) have recently demonstrated impressive performance on complex, multi-step reasoning tasks, especially when post-trained with outcome-rewarded reinforcement learning Guo et al. 2025. However, it has been observed…
Large language models (LLM) often hallucinate, and while adding citations is a common solution, it is frequently insufficient for accountability as users struggle to verify how a cited source supports a generated claim. Existing methods are…
In an era increasingly dominated by digital platforms, the spread of misinformation poses a significant challenge, highlighting the need for solutions capable of assessing information veracity. Our research contributes to the field of…
Large Language Models (LLMs) show impressive inductive reasoning capabilities, enabling them to generate hypotheses that could generalize effectively to new instances when guided by in-context demonstrations. However, in real-world…
Maintaining large code bases written in dynamically typed languages, such as JavaScript or Python, can be challenging due to the absence of type annotations: simple data compatibility errors proliferate, IDE support is limited, and APIs are…
We further develop the theoretical framework of proof mining, a program in mathematical logic that seeks to quantify and extract computational information from prima facie `non-computational' proofs from the mainstream mathematical…
Formally verifying software properties is a highly desirable but labor-intensive task. Recent work has developed methods to automate formal verification using proof assistants, such as Coq and Isabelle/HOL, e.g., by training a model to…
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…
To ensure large language models (LLMs) are used safely, one must reduce their propensity to hallucinate or to generate unacceptable answers. A simple and often used strategy is to first let the LLM generate multiple hypotheses and then…
Generative neural networks have been shown effective on query suggestion. Commonly posed as a conditional generation problem, the task aims to leverage earlier inputs from users in a search session to predict queries that they will likely…
Formal languages let us define the textual representation of data with precision. Formal grammars, typically in the form of BNF-like productions, describe the language syntax, which is then annotated for syntax-directed translation and…
Deep generative models are able to suggest new organic molecules by generating strings, trees, and graphs representing their structure. While such models allow one to generate molecules with desirable properties, they give no guarantees…
Argumentation accommodates various rhetorical devices, such as questions, reported speech, and imperatives. These rhetorical tools usually assert argumentatively relevant propositions rather implicitly, so understanding their true meaning…
We take inspiration from the study of human explanation to inform the design and evaluation of interpretability methods in machine learning. First, we survey the literature on human explanation in philosophy, cognitive science, and the…
Understanding and creating mathematics using natural mathematical language - the mixture of symbolic and natural language used by humans - is a challenging and important problem for driving progress in machine learning. As a step in this…
We introduce LeanConjecturer, a pipeline for automatically generating university-level mathematical conjectures in Lean 4 using Large Language Models (LLMs). Our hybrid approach combines rule-based context extraction with LLM-based theorem…
Knowledge-enhanced text generation aims to enhance the quality of generated text by utilizing internal or external knowledge sources. While language models have demonstrated impressive capabilities in generating coherent and fluent text,…
Recent developments in transformer-based language models have allowed them to capture a wide variety of world knowledge that can be adapted to downstream tasks with limited resources. However, what pieces of information are understood in…
Large Language Models (LLMs) demonstrate impressive mathematical reasoning abilities, but their solutions frequently contain errors that cannot be automatically checked. Formal theorem proving systems such as Lean 4 offer automated…