Skip to content

Commit 508a4df

Browse files
committed
Adding arXiv cite to README.md.
1 parent e847fce commit 508a4df

File tree

1 file changed

+15
-3
lines changed

1 file changed

+15
-3
lines changed

README.md

Lines changed: 15 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# VerilogEval Overview
22

3-
This is an evaluation harness for the VerilogEval problem solving dataset originally described in the paper "[VerilogEval: Evaluating Large Language Models for Verilog Code Generation](https://arxiv.org/abs/2309.07544)," published in 2023. In August 2024, this repository was revised to cover specification-to-RTL tasks in addition to the original code completion task, add in-context learning examples to prompts, and categorize common iverilog failures.
3+
This is an evaluation harness for the VerilogEval problem solving dataset originally described in the paper "[VerilogEval: Evaluating Large Language Models for Verilog Code Generation](https://arxiv.org/abs/2309.07544)," published in 2023. In August 2024, this repository was revised to cover specification-to-RTL tasks in addition to the original code completion task, add in-context learning examples to prompts, and categorize common iverilog failures. Please see the related apaper "[Revisiting VerilogEval: Newer LLMs, In-Context Learning, and Specification-to-RTL Tasks](https://arxiv.org/abs/2408.11053)," published in 2024.
44

55
**If you would like to benchmark against the original VerilogEval 1.0 harness, please checkout Git branch "release/1.0.0" which has been kept to preserve this original benchmark. Otherwise, the main branch can be used for the improved harness.**
66

@@ -73,9 +73,21 @@ These parameters can be easily swept with a shell script, to create separate bui
7373

7474
## Citation
7575

76-
The arXiv paper is forthcoming and we will provide a citation for VerilogEvalv2 shortly.
76+
For this VerilogEval v2, please cite the following paper:
7777

78-
For VerilogEval v1 please use:
78+
```
79+
@misc{pinckney2024revisitingverilogevalnewerllms,
80+
title={Revisiting VerilogEval: Newer LLMs, In-Context Learning, and Specification-to-RTL Tasks},
81+
author={Nathaniel Pinckney and Christopher Batten and Mingjie Liu and Haoxing Ren and Brucek Khailany},
82+
year={2024},
83+
eprint={2408.11053},
84+
archivePrefix={arXiv},
85+
primaryClass={cs.SE},
86+
url={https://arxiv.org/abs/2408.11053},
87+
}
88+
```
89+
90+
For the original VerilogEval v1, please use:
7991

8092
```
8193
@inproceedings{liu2023verilogeval,

0 commit comments

Comments
 (0)