Papers with Teaching large language models

3 papers
Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning (2025.naacl-long)

Copied to clipboard

Challenge: Teaching large language models to use tools for solving complex problems can grant them human-like reasoning abilities.
Approach: They propose a multi-agent system that enhances the Deep First Search Decision Tree (DFSDT) to address issues like error propagation and limited exploration in ReAct .
Outcome: The proposed system reduces token usage by 60.9% compared to existing methods and performs on par with GPT-4-DFSDT.
Towards Improved Multi-Source Attribution for Long-Form Answer Generation (2024.naacl-long)

Copied to clipboard

Challenge: Current LLMs struggle with attribution for long-form answers which require reasoning over multiple evidence sources.
Approach: They propose to improve attribution capability of large language models for long-form answer generation to multiple sources with multiple citations per sentence.
Outcome: The proposed model improves on a wide range of attribution benchmark datasets on PolitiICite, a multi-source attribution dataset based on PolitIcite articles .
Advancing Large Language Model Attribution through Self-Improving (2024.emnlp-main)

Copied to clipboard

Challenge: Teaching large language models to generate text with citations to evidence sources requires high-quality attribution data, which is costly and labor-intensive.
Approach: They propose a framework for iteratively improving the attribution capability of large language models (LLMs) by attributing output to verifiable sources.
Outcome: Experiments on three open-domain question-answering datasets show that START improves in aggregating information across multiple sources.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations