Update README.md

README.md

@@ -13,20 +13,23 @@ Code: https://github.com/fengbinzhu/TAT-LLM
 
 ## Introduction
 
-We present TAT-LLM, a specialized language model crafted through the innovative Step-wise Pipeline approach, focusing on the nuanced realm of tabular and textual question answering (QA). This model is the fruit of rigorously fine-tuning the LLaMA 2 architecture with a novel dataset, autonomously generated from expertly annotated resources. TAT-LLM stands at the intersection of tabular comprehension and textual analysis, engineered to excel by embodying three fundamental phases: Extraction, Reasoning, and Execution. Our empirical findings illuminate TAT-LLM's remarkable capability to eclipse traditional benchmarks, surmounting even the most advanced models and colossal language models such as GPT-4 across a suite of demanding QA tasks like FinQA, TAT-QA, and TAT-DQA. This endeavor not only sets a new standard for task-specific language models but also paves the way for future explorations in optimizing smaller models for highly specialized functions.
+We present TAT-LLM, a specialized language model crafted through the innovative Step-wise Pipeline approach, focusing on the nuanced realm of tabular and textual question answering (QA). This model is the fruit of rigorously fine-tuning the LLaMA 2 architecture with a novel dataset, autonomously generated from expertly annotated resources. TAT-LLM stands at the intersection of tabular comprehension and textual analysis, engineered to excel by embodying three fundamental phases: Extraction, Reasoning, and Execution. Our empirical findings illuminate TAT-LLM's remarkable capability to eclipse traditional benchmarks, surmounting even the most advanced models and colossal language models such as GPT-4 across a suite of demanding financial QA tasks like FinQA, TAT-QA, and TAT-DQA. This endeavor not only sets a new standard for task-specific language models but also paves the way for future explorations in optimizing smaller models for highly specialized functions.
 
 | Model | Size | FINQA | TATQA | TATDQA |
 | ---   | ---  | ---   | ---   | ---    |
 | GPT-3.5-Turbo | - | 58.00 | 59.47 | 52.74 |
 | GPT-4 | - | 63.91 | 71.92 | 64.46 |
-| TAT-LLM-7B | 7B | 65.13 | 76.49 | 71.38 |
-| TAT-LLM-13B | 13B | 71.93 | 77.51 | 72.22 |
-| TAT-LLM-70B | 70B | **76.81** | **81.42** | **76.55** |
+| TAT-LLM-7B-LORA | 7B | 65.13 | 76.49 | 71.38 |
+| TAT-LLM-7B-FFT | 7B | 69.75 | 76.91 | 72.64 |
+| TAT-LLM-13B-LORA | 13B | 71.93 | 77.51 | 72.22 |
+| TAT-LLM-13B-FFT | 13B | 72.97 | 78.41 | 73.18 |
+| TAT-LLM-70B-LORA | 70B | **76.81** | 81.42 | 76.55 |
+| TAT-LLM-70B-FFT | 70B | 76.11 | **82.20** | **76.97** |
 
 
 ## Training
 
-We train our TAT-LLM model in various sizes, including 7B, 13B, and 70B, by fine-tuning LLaMA 2 using Low-Rank Adaptation (LoRa) on a combination of the train sets from FinQA, TAT-QA and TAT-DQA datasets. To refine accuracy, we introduce an External Executor, enhancing the model by processing intermediate outputs to derive conclusive answers. Please refer to the [paper](https://arxiv.org/abs/2401.13223) for more details.
+We train our TAT-LLM model in various sizes, including 7B, 13B, and 70B, using different methods such as parameter-efficient fine-tuning and full-parameter fine-tuning of LLaMA 2 on a combination of financial data from the FinQA, TAT-QA, and TAT-DQA datasets. To refine accuracy, we introduce an External Executor, enhancing the model by processing intermediate outputs to derive conclusive answers. Please refer to the [paper](https://arxiv.org/abs/2401.13223) for more details.
 
 ## Inference & Evaluation
 
@@ -34,7 +37,7 @@ Please refer to code [here](https://github.com/fengbinzhu/TAT-LLM)
 
 ## Citation
 
-If you find this repository helpful, please consider citing our paper:
+If you find this model helpful, please consider citing our paper:
 
 ```
 @misc{zhu2024tatllm,