110 citations · 245 across the 14 of their papers we have counts for
7 papers · 1 filter
Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback
Nearchos Potamitis, Akhil Arora
Recent advancements in large language models (LLMs) have catalyzed the development of general-purpose autonomous agents, demonstrating remarkable performance in complex reasoning t…
Entity Insertion in Multilingual Linked Corpora: The Case of Wikipedia
Tomás Feith, Akhil Arora, Martin Gerlach +2
Links are a fundamental part of information networks, turning isolated pieces of knowledge into a network of information that is much richer than the sum of its parts. However, add…
Fleet of Agents: Coordinated Problem Solving with Large Language Models
Lars Klein, Nearchos Potamitis, Roland Aydin +3
While numerous frameworks have been developed to enhance the reasoning abilities of large language models (LLMs), there is a scarcity of methods that effectively balance the trade-…
Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science
Veniamin Veselovsky, Manoel Horta Ribeiro, Akhil Arora +3
Large Language Models (LLMs) have democratized synthetic data generation, which in turn has the potential to simplify and broaden a wide gamut of NLP tasks. Here, we tackle a perva…
Strong Heuristics for Named Entity Linking
Marko Čuljak, Andreas Spitz, Robert West +1
Named entity linking (NEL) in news is a challenging endeavour due to the frequency of unseen and emerging entities, which necessitates the use of unsupervised or zero-shot methods.…
Efficient Entity Candidate Generation for Low-Resource Languages
Alberto García-Durán, Akhil Arora, Robert West
Candidate generation is a crucial module in entity linking. It also plays a key role in multiple NLP tasks that have been proven to beneficially leverage knowledge bases. Neverthel…
Low-Rank Subspaces for Unsupervised Entity Linking
Akhil Arora, Alberto García-Durán, Robert West
Entity linking is an important problem with many applications. Most previous solutions were designed for settings where annotated training data is available, which is, however, not…