Related papers: Project SHADOW: Symbolic Higher-order Associative …
This paper presents our findings of the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes, MU-SHROOM, which focuses on identifying hallucinations and related overgeneration errors in large language…
Graph-based semi-supervised learning has proven to be an effective approach for query-focused multi-document summarization. The problem of previous semi-supervised learning is that sentences are ranked without considering the higher level…
Speculative decoding is a technique that uses multiple language models to accelerate infer- ence. Previous works have used an experi- mental approach to optimize the throughput of the inference pipeline, which involves LLM training and can…
LLMs deployed for natural-language querying of analytical databases suffer from two intertwined failures - incorrect answers and confident hallucinations - both rooted in the same cause: the model is forced to infer business semantics that…
Multimodal reasoning has become a cornerstone of modern AI research. Standardized exam questions offer a uniquely rigorous testbed for such reasoning, providing structured visual contexts and verifiable answers. While recent progress has…
Large Language Models (LLMs) have achieved impressive performance in complex reasoning problems. Their effectiveness highly depends on the specific nature of the task, especially the required domain knowledge. Existing approaches, such as…
Conversational multi-doc question answering aims to answer specific questions based on the retrieved documents as well as the contextual conversations. In this paper, we introduce our winning approach for the "Conversational Multi-Doc QA"…
In-context learning (ICL) is a powerful paradigm where large language models (LLMs) benefit from task demonstrations added to the prompt. Yet, selecting optimal demonstrations is not trivial, especially for complex or multi-modal tasks…
Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks, but they still struggle with some complicated reasoning tasks including logical reasoning. One non-negligible reason for LLMs' suboptimal performance…
Recently proposed speech recognition systems are designed to predict using representations generated by their top layers, employing greedy decoding which isolates each timestep from the rest of the sequence. Aiming for improved performance,…
Recent advancements in language models have demonstrated remarkable improvements in various natural language processing (NLP) tasks such as web navigation. Supervised learning (SL) approaches have achieved impressive performance while…
This paper describes our contribution to the SemEval-2020 Task 9 on Sentiment Analysis for Code-mixed Social Media Text. We investigated two approaches to solve the task of Hinglish sentiment analysis. The first approach uses cross-lingual…
When people answer questions about a specific situation, e.g., "I cheated on my mid-term exam last week. Was that wrong?", cognitive science suggests that they form a mental picture of that situation before answering. While we do not know…
Fact verification based on structured data is challenging as it requires models to understand both natural language and symbolic operations performed over tables. Although pre-trained language models have demonstrated a strong capability in…
Tabular reasoning involves multi-step information extraction and logical inference over tabular data. While recent advances have leveraged large language models (LLMs) for reasoning over structured tables, such high-quality textual…
Semi-Supervised Semantic Segmentation reduces reliance on extensive annotations by using unlabeled data and state-of-the-art models to improve overall performance. Despite the success of deep co-training methods, their underlying mechanisms…
A SNoW based learning approach to shallow parsing tasks is presented and studied experimentally. The approach learns to identify syntactic patterns by combining simple predictors to produce a coherent inference. Two instantiations of this…
The performance of object detection, to a great extent, depends on the availability of large annotated datasets. To alleviate the annotation cost, the research community has explored a number of ways to exploit unlabeled or weakly labeled…
This paper describes the LIAAD system that was ranked second place in the Word-in-Context challenge (WiC) featured in SemDeep-5. Our solution is based on a novel system for Word Sense Disambiguation (WSD) using contextual embeddings and…
Multimodal reasoning, which integrates language and visual cues into problem solving and decision making, is a fundamental aspect of human intelligence and a crucial step toward artificial general intelligence. However, the evaluation of…