Model Card for TG-LLM

TG-LLM consists of supervised fine-tuned models designed for temporal reasoning with large language models (LLMs). It includes two primary tasks:

1. Story-to-Temporal-Graph Translation (story_TG_trans) – converting a narrative into its corresponding temporal graph.
2. Temporal-Graph Reasoning (TGR) – reasoning over a given temporal graph to answer questions.

Model Details

TGQA_story_TG_trans

• Base Model: meta-llama/Llama-2-13b-chat-hf

• LoRA Configuration:

  • lora_alpha: 8
  • r: 8
  • target_modules: ["q_proj", "k_proj", "o_proj", "v_proj"]
  • bias: "none"

TGQA_TGR

• Base Model: meta-llama/Llama-2-13b-chat-hf

• LoRA Configuration:

  • lora_alpha: 8
  • r: 8
  • target_modules: ["q_proj", "k_proj", "o_proj", "v_proj"]
  • bias: "none"

For more details, please visit the TG-LLM GitHub repository.

Citation

@inproceedings{xiong-etal-2024-large,
    title = "Large Language Models Can Learn Temporal Reasoning",
    author = "Xiong, Siheng  and
      Payani, Ali  and
      Kompella, Ramana  and
      Fekri, Faramarz",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.acl-long.563",
    doi = "10.18653/v1/2024.acl-long.563",
    pages = "10452--10470"
}