tikendraw commited on
Commit
55d6387
·
1 Parent(s): 6f1c279

readme updated

Browse files
Files changed (1) hide show
  1. README.md +31 -5
README.md CHANGED
@@ -8,11 +8,12 @@ It thinks like o1
8
  [ ] Better error handling
9
  [ ] Add Tools (web, math, code)
10
  [ ] Make cli
11
-
12
 
13
  ## What it does
14
 
15
- - It takes a prompt , thinks, thinks again, critics itself, then returns answer
 
16
 
17
  ## Installation
18
 
@@ -28,10 +29,31 @@ HAVE FUN.
28
 
29
  ## Helpful Papers
30
 
31
- 1. To Cot or not to Cot? CHAIN-OF-THOUGHT HELPS MAINLY ON MATH AND SYMBOLIC REASONING
 
 
 
 
 
 
 
 
 
 
 
32
 
33
  2. The Impact of Reasoning Step Length on Large Language Models
34
-
 
 
 
 
 
 
 
 
 
 
35
  3. Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters [2212.10001](https://arxiv.org/abs/2212.10001)
36
  ```bibtex
37
  @misc{wang2023understandingchainofthoughtpromptingempirical,
@@ -43,4 +65,8 @@ HAVE FUN.
43
  primaryClass={cs.CL},
44
  url={https://arxiv.org/abs/2212.10001},
45
  }
46
- ```
 
 
 
 
 
8
  [ ] Better error handling
9
  [ ] Add Tools (web, math, code)
10
  [ ] Make cli
11
+ [ ] better prompts for mathematical reasoning/reviewing
12
 
13
  ## What it does
14
 
15
+ - It taks the prompt, decides whether to use chain of thought or direct answer, if cot then generates answer and does self review, if direct answer then directly generates answer.
16
+ - Mathematical reasoning, symbolic reasoning and semi-symbolic reasoning kind of tasks generally improves with chain of thought, but direct answer is good for factual recall, simple inferences, commonsense reasoning, language understanding tasks.
17
 
18
  ## Installation
19
 
 
29
 
30
  ## Helpful Papers
31
 
32
+ 1. To Cot or not to Cot? CHAIN-OF-THOUGHT HELPS MAINLY ON MATH AND SYMBOLIC REASONING
33
+ ```bibtex
34
+ @misc{sprague2024cotcotchainofthoughthelps,
35
+ title={To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning},
36
+ author={Zayne Sprague and Fangcong Yin and Juan Diego Rodriguez and Dongwei Jiang and Manya Wadhwa and Prasann Singhal and Xinyu Zhao and Xi Ye and Kyle Mahowald and Greg Durrett},
37
+ year={2024},
38
+ eprint={2409.12183},
39
+ archivePrefix={arXiv},
40
+ primaryClass={cs.CL},
41
+ url={https://arxiv.org/abs/2409.12183},
42
+ }
43
+ ```
44
 
45
  2. The Impact of Reasoning Step Length on Large Language Models
46
+ ```bibtex
47
+ @misc{jin2024impactreasoningsteplength,
48
+ title={The Impact of Reasoning Step Length on Large Language Models},
49
+ author={Mingyu Jin and Qinkai Yu and Dong Shu and Haiyan Zhao and Wenyue Hua and Yanda Meng and Yongfeng Zhang and Mengnan Du},
50
+ year={2024},
51
+ eprint={2401.04925},
52
+ archivePrefix={arXiv},
53
+ primaryClass={cs.CL},
54
+ url={https://arxiv.org/abs/2401.04925},
55
+ }
56
+ ```
57
  3. Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters [2212.10001](https://arxiv.org/abs/2212.10001)
58
  ```bibtex
59
  @misc{wang2023understandingchainofthoughtpromptingempirical,
 
65
  primaryClass={cs.CL},
66
  url={https://arxiv.org/abs/2212.10001},
67
  }
68
+ ```
69
+
70
+ # But me a Coffee
71
+
72
+ [!["Buy Me A Coffee"](https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png)](https://buymeacoffee.com/tikendraw)