Related papers: Dynamic Type Inference for Gradual Hindley--Milner…

Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across a wide range of NLP tasks, yet they remain prone to factual inaccuracies and hallucinations. This limitation poses significant risks in high-stakes…

Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through an iterative denoising process, DLMs possess inherent…

In the theory of programming languages, type inference is the process of inferring the type of an expression automatically, often making use of information from the context in which the expression appears. Such mechanisms turn out to be…

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Text infilling is defined as a task for filling in the missing part of a sentence or paragraph, which is suitable for many real-world natural language generation scenarios. However, given a well-trained sequential generative model,…

There has been growing interest in automatically predicting missing type annotations in programs written in Python and JavaScript. While prior methods have achieved impressive accuracy when predicting the most common types, they often…

Large pretrained language models have shown surprising in-context learning (ICL) ability. With a few demonstration input-label pairs, they can predict the label for an unseen input without parameter updates. Despite the great success in…

Syntactic Transformer language models aim to achieve better generalization through simultaneously modeling syntax trees and sentences. While prior work has been focusing on adding constituency-based structures to Transformers, we introduce…

A key challenge when statically typing so-called dynamic languages is the ubiquity of value-based overloading, where a given function can dynamically reflect upon and behave according to the types of its arguments. Thus, to establish basic…

Text-video retrieval is a critical multi-modal task to find the most relevant video for a text query. Although pretrained models like CLIP have demonstrated impressive potential in this area, the rising cost of fully finetuning these models…

We present cTI, the first system for universal left-termination inference of logic programs. Termination inference generalizes termination analysis and checking. Traditionally, a termination analyzer tries to prove that a given class of…

Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of introspective consistency: AR models agree with their own generations, while DLMs often do…

Large language models (LLM), such as Google's Minerva and OpenAI's GPT families, are becoming increasingly capable of solving mathematical quantitative reasoning problems. However, they still make unjustified logical and computational…

Large language models (LMs) are capable of in-context learning from a few demonstrations (example-label pairs) to solve new tasks during inference. Despite the intuitive importance of high-quality demonstrations, previous work has observed…

In a previous work Baillot and Terui introduced Dual light affine logic (DLAL) as a variant of Light linear logic suitable for guaranteeing complexity properties on lambda calculus terms: all typable terms can be evaluated in polynomial…

Recent studies have introduced a new class of generative models for synthesizing implicit neural representations (INRs) that capture arbitrary continuous signals in various domains. These models opened the door for domain-agnostic…

Effective incident response (IR) is critical for mitigating cyber threats, yet security teams are overwhelmed by alert fatigue, high false-positive rates, and the vast volume of unstructured Cyber Threat Intelligence (CTI) documents. While…

We study the problem of generating plans for given natural language planning task requests. On one hand, LLMs excel at natural language processing but do not perform well on planning. On the other hand, classical planning tools excel at…

Interpretable text representations should expose coordinates that are not only predictive, but also meaningful enough for independent auditors to apply. Existing discriminative representations often use anonymous embedding directions, while…

Type-and-effect systems help the programmer to organize data and computational effects in a program. While for traditional type systems expressive variants with sophisticated inference algorithms have been developed and widely used in…