Related papers: Intensionalizing Abstract Meaning Representations:…
Large language models (LLMs) are increasingly used for program verification, and yet little is known about \emph{how} they reason about program semantics during this process. In this work, we focus on abstract interpretation based-reasoning…
In this paper, we consider two of the currently popular semantic frameworks: Abstract Meaning Representation (AMR)a more abstract framework, and Universal Conceptual Cognitive Annotation (UCCA)-an anchored framework. We use a corpus-based…
Abstract meaning representation (AMR) highlights the core semantic information of text in a graph structure. Recently, pre-trained language models (PLMs) have advanced tasks of AMR parsing and AMR-to-text generation, respectively. However,…
Detailed image captioning is essential for tasks like data generation and aiding visually impaired individuals. High-quality captions require a balance between precision and recall, which remains challenging for current multimodal large…
In this thesis we present a semantic representation formalism based on directed graphs and explore its linguistic adequacy and explanatory benefits in the semantics of plurality and quantification. Our graph language covers the essentials…
The Abstraction and Reasoning Corpus (ARC) is a challenging benchmark, introduced to foster AI research towards human-level intelligence. It is a collection of unique tasks about generating colored grids, specified by a few examples only.…
Images usually convey richer detail than text, but often include redundant information, which potentially downgrades multimodal reasoning performance. When faced with lengthy or complex messages, humans tend to employ abstract thinking to…
Large-scale Vision-Language Models (VLMs) such as CLIP learn powerful semantic representations but operate in Euclidean space, which fails to capture the inherent hierarchical structure of visual and linguistic concepts. Hyperbolic…
Large language models (LLMs) demonstrate strong performance in math reasoning benchmarks, but their performance varies inconsistently across problems with varying levels of difficulty. This paper describes Adaptive Multi-Expert Reasoning…
This paper evaluates the ability of Large Language Models (LLMs) to leverage contextual information in the form of structured linguistic representations. Specifically, we examine the impact of encoding both short and long contexts using…
Multimodal Mathematical Reasoning (MMR) has recently attracted increasing attention for its capability to solve mathematical problems involving both textual and visual modalities. However, current models still face significant challenges in…
Artificial intelligence and machine learning systems have demonstrated huge improvements and human-level parity in a range of activities, including speech recognition, face recognition and speaker verification. However, these diverse tasks…
Semantic role labeling (SRL) involves extracting propositions (i.e. predicates and their typed arguments) from natural language sentences. State-of-the-art SRL models rely on powerful encoders (e.g., LSTMs) and do not model non-local…
Implicit neural representations (INRs) mark a fundamental shift in signal modeling, moving from discrete sampled data to continuous functional representations. By parameterizing signals as neural networks, INRs provide a unified framework…
AMR-to-text is one of the key techniques in the NLP community that aims at generating sentences from the Abstract Meaning Representation (AMR) graphs. Since AMR was proposed in 2013, the study on AMR-to-Text has become increasingly…
We present abstract acceleration techniques for computing loop invariants for numerical programs with linear assignments and conditionals. Whereas abstract interpretation techniques typically over-approximate the set of reachable states…
Pre-trained language models have made great progress on dialogue tasks. However, these models are typically trained on surface dialogue text, thus are proven to be weak in understanding the main semantic meaning of a dialogue context. We…
Current methods for Black-Box NLP interpretability, like LIME or SHAP, are based on altering the text to interpret by removing words and modeling the Black-Box response. In this paper, we outline limitations of this approach when using…
Large reasoning models (LRMs) often generate long, seemingly coherent reasoning traces yet still produce incorrect answers, making hallucination detection challenging. Although trajectories contain useful signals, directly using trace text…
Abstraction--the ability to recognize and distill essential computational patterns from complex problem statements--is a foundational skill in computer science, critical both for human problem-solvers and coding-oriented large language…