Papers by Marcio Fonseca
Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals? (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent work on the evaluation of large language models (LLMs) has shown unprecedented performance on diverse language generation tasks. |
| Approach: | They investigate the controllability of large language models on scientific summarization tasks by controlling stylistic and content coverage factors. |
| Outcome: | The proposed model outperforms humans on the MuP review generation task in terms of similarity to reference summaries and human preferences. |
LeanReasoner: Boosting Complex Logical Reasoning with Lean (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) often struggle with complex logical reasoning due to logical inconsistencies and the inherent difficulty of such reasoning. |
| Approach: | They propose a method that formalizes logical reasoning problems into theorems within Lean and then proves or disproving the corresponding theorels. |
| Outcome: | The proposed method achieves state-of-the-art performance on the FOLIO dataset and near this level on ProofWriter. |
Can Large Language Models Follow Concept Annotation Guidelines? A Case Study on Scientific and Financial Domains (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are known to distill knowledge from vast datasets during the pretraining phase. |
| Approach: | They propose to use in-context concept definitions as prompts for zero-shot sentence labeling tasks. |
| Outcome: | The proposed model outperforms the leading open-source models and their proprietary APIs in most cases. |
Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents (2022.emnlp-main)
Copied to clipboard
| Challenge: | Using a factorization approach, summarization decisions are conflated into a single feedforward step without taking into account contextual factors. |
| Approach: | They propose to factorize summarization into two steps following a budget and content guidance. |
| Outcome: | The proposed method outperforms PEGASUS in domain adaptation and generates significantly higher ROUGE scores on multiple benchmarks for long document summarization. |