Assessing Open-Source Large Language Models on Argumentation Mining Subtasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915009981841408 |
|---|---|
| author | Abkenar, Mohammad Yeghaneh Wang, Weixing Graupner, Hendrik Stede, Manfred |
| author_facet | Abkenar, Mohammad Yeghaneh Wang, Weixing Graupner, Hendrik Stede, Manfred |
| contents | We explore the capability of four open-sourcelarge language models (LLMs) in argumentation mining (AM). We conduct experiments on three different corpora; persuasive essays(PE), argumentative microtexts (AMT) Part 1 and Part 2, based on two argumentation mining sub-tasks: (i) argumentative discourse units classifications (ADUC), and (ii) argumentative relation classification (ARC). This work aims to assess the argumentation capability of open-source LLMs, including Mistral 7B, Mixtral8x7B, LlamA2 7B and LlamA3 8B in both, zero-shot and few-shot scenarios. Our analysis contributes to further assessing computational argumentation with open-source LLMs in future research efforts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_05639 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Assessing Open-Source Large Language Models on Argumentation Mining Subtasks Abkenar, Mohammad Yeghaneh Wang, Weixing Graupner, Hendrik Stede, Manfred Computation and Language We explore the capability of four open-sourcelarge language models (LLMs) in argumentation mining (AM). We conduct experiments on three different corpora; persuasive essays(PE), argumentative microtexts (AMT) Part 1 and Part 2, based on two argumentation mining sub-tasks: (i) argumentative discourse units classifications (ADUC), and (ii) argumentative relation classification (ARC). This work aims to assess the argumentation capability of open-source LLMs, including Mistral 7B, Mixtral8x7B, LlamA2 7B and LlamA3 8B in both, zero-shot and few-shot scenarios. Our analysis contributes to further assessing computational argumentation with open-source LLMs in future research efforts. |
| title | Assessing Open-Source Large Language Models on Argumentation Mining Subtasks |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2411.05639 |