Related papers: Emphasising Structured Information: Integrating Ab…
Offline evaluation of search systems depends on test collections. These benchmarks provide the researchers with a corpus of documents, topics and relevance judgements indicating which documents are relevant for each topic. While test…
The production of digital documents has been growing rapidly in academic, business, and health environments, presenting new challenges in the efficient extraction and analysis of unstructured information. This work investigates the use of…
Metaphor is a pervasive feature of discourse and a powerful lens for examining cognition, emotion, and ideology. Large-scale analysis, however, has been constrained by the need for manual annotation due to the context-sensitive nature of…
Abstract Meaning Representation (AMR) is a Semantic Parsing formalism that aims at providing a semantic graph abstraction representing a given text. Current approaches are based on autoregressive language models such as BART or T5,…
We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from heterogeneous sources like text, knowledge graphs, tables, and infoboxes. Our…
Generating text from structured data is challenging because it requires bridging the gap between (i) structure and natural language (NL) and (ii) semantically underspecified input and fully specified NL output. Multilingual generation…
Conversational systems should generate diverse language forms to interact fluently and accurately with users. In this context, Natural Language Generation (NLG) engines convert Meaning Representations (MRs) into sentences, directly…
Large language models (LLMs) have significantly transformed the educational landscape. As current plagiarism detection tools struggle to keep pace with LLMs' rapid advancements, the educational community faces the challenge of assessing…
Recent advances in test-time scaling have shown promising results in improving Large Language Model (LLM) performance through strategic computation allocation during inference. While this approach has demonstrated strong improvements in…
We attempt to solve the Abstraction and Reasoning Corpus (ARC) Challenge using Large Language Models (LLMs) as a system of multiple expert agents. Using the flexibility of LLMs to be prompted to do various novel tasks using zero-shot,…
The evaluation of Large Language Models (LLMs) increasingly relies on other LLMs acting as judges. However, current evaluation paradigms typically yield a single score or ranking, answering which model is better but not why. While essential…
Evaluating the quality of arguments is a crucial aspect of any system leveraging argument mining. However, it is a challenge to obtain reliable and consistent annotations regarding argument quality, as this usually requires domain-specific…
Reliable evaluation of large language model (LLM)-generated summaries remains an open challenge, particularly across heterogeneous domains and document lengths. We conduct a comprehensive meta-evaluation of 14 automatic summarization…
In this paper, we present a novel diagnostic framework that integrates Knowledge Graphs (KGs) and Large Language Models (LLMs) to support system diagnostics in high-reliability systems such as nuclear power plants. Traditional diagnostic…
Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. However, analyzing live dialogues in real-time necessitates low-latency processing…
Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training…
Language models are typically evaluated on their success at predicting the distribution of specific words in specific contexts. Yet linguistic knowledge also encodes relationships between contexts, allowing inferences between word…
In this project, we test the effectiveness of Large Language Models (LLMs) on the Abstraction and Reasoning Corpus (ARC) dataset. This dataset serves as a representative benchmark for testing abstract reasoning abilities, requiring a…
Recent advancements in Chain-of-Thought prompting have facilitated significant breakthroughs for Large Language Models (LLMs) in complex reasoning tasks. Current research enhances the reasoning performance of LLMs by sampling multiple…
While integrating speech encoder with LLM requires substantial data and resources, use cases face limitations due to insufficient availability. To address this, we propose a solution with a parameter-efficient adapter that converts speech…