54 citations · 63 across the 9 of their papers we have counts for
11 papers
Graph Serializations for Reasoning LLMs: A Study Across Knowledge Extraction and Structural Reasoning
Julien Yu, Mihaela Bornea, Avirup Sil +1
The way a knowledge graph is serialized as text for inclusion into LLM context can substantially affect downstream LLM performance, with prior work reporting tens of percentage poi…
SeaView: Software Engineering Agent Visual Interface for Enhanced Workflow
Timothy Bula, Saurabh Pujar, Luca Buratti +2
Auto-regressive LLM-based software engineering (SWE) agents, henceforth SWE agents, have made tremendous progress (>60% on SWE-Bench Verified) on real-world coding challenges inclu…
Granite Embedding Models
Parul Awasthy, Aashka Trivedi, Yulong Li +19
We introduce the Granite Embedding models, a family of encoder-based embedding models designed for retrieval tasks, spanning dense-retrieval and sparse retrieval architectures, wit…
PrimeQA: The Prime Repository for State-of-the-Art Multilingual Question Answering Research and Development
Avirup Sil, Jaydeep Sen, Bhavani Iyer +12
The field of Question Answering (QA) has made remarkable progress in recent years, thanks to the advent of large pre-trained language models, newer realistic benchmark datasets wit…
GAAMA 2.0: An Integrated System that Answers Boolean and Extractive Questions
Scott McCarley, Mihaela Bornea, Sara Rosenthal +4
Recent machine reading comprehension datasets include extractive and boolean questions but current approaches do not offer integrated support for answering both question types. We…
Do Answers to Boolean Questions Need Explanations? Yes
Sara Rosenthal, Mihaela Bornea, Avirup Sil +2
Existing datasets that contain boolean questions, such as BoolQ and TYDI QA , provide the user with a YES/NO response to the question. However, a one word response is not sufficien…
Learning to Transpile AMR into SPARQL
Mihaela Bornea, Ramon Fernandez Astudillo, Tahira Naseem +5
We propose a transition-based system to transpile Abstract Meaning Representation (AMR) into SPARQL for Knowledge Base Question Answering (KBQA). This allows us to delegate part of…
Generative Relation Linking for Question Answering over Knowledge Bases
Gaetano Rossiello, Nandana Mihindukulasooriya, Ibrahim Abdelaziz +4
Relation linking is essential to enable question answering over knowledge bases. Although there are various efforts to improve relation linking performance, the current state-of-th…
Are Multilingual BERT models robust? A Case Study on Adversarial Attacks for Multilingual Question Answering
Sara Rosenthal, Mihaela Bornea, Avirup Sil
Recent approaches have exploited weaknesses in monolingual question answering (QA) models by adding adversarial statements to the passage. These attacks caused a reduction in state…
Multilingual Transfer Learning for QA Using Translation as Data Augmentation
Mihaela Bornea, Lin Pan, Sara Rosenthal +2
Prior work on multilingual question answering has mostly focused on using large multilingual pre-trained language models (LM) to perform zero-shot language-wise learning: train a Q…
Exploring Software Naturalness through Neural Language Models
Luca Buratti, Saurabh Pujar, Mihaela Bornea +8
The Software Naturalness hypothesis argues that programming languages can be understood through the same techniques used in natural language processing. We explore this hypothesis…