allenai / digital-socrates-13b

huggingface.co
Total runs: 1.9K
24-hour runs: 0
7-day runs: -31
30-day runs: 854
Model's Last Updated: Setembro 02 2024
text-generation

Introduction of digital-socrates-13b

Model Details of digital-socrates-13b

This is the Digital Socrates 13B (DS-13B) model described in our paper: Digital Socrates: Evaluating LLMs through explanation critiques (arXiv link: https://arxiv.org/abs/2311.09613 ).

The less recommended, smaller 7B model can be found at https://huggingface.co/allenai/digital-socrates-7b

The DS-13B model is a fine-tuned version of Llama-2-13b-Chat , please review its guidelines and licensing before use.

What is Digital Socrates?

Digital Socrates is an open-source, automatic explanation-critiquing model. It is useful for revealing insights about student models by examining their reasoning chains. The use of Digital Socrates allows for nuanced, interpretable automatic evaluation of explanations without expensive API calls or human annotations.

While LLMs can provide reasoned explanations along with their answers, the nature and quality of those explanations are still poorly understood. In response, our goal is to define a detailed way of characterizing the explanation capabilities of modern models and to create a nuanced, interpretable explanation evaluation tool that can generate such characterizations automatically.

Given a question (together with the multiple-choice options and gold answer),

When Dennis operates his lawnmower, he notices the engine makes a lot of noise. He also notices that the engine gets very hot. Which best describes the heat and noise generated from the lawnmower? 
(A) a change in phase 
(B) thermal expansion 
(C) an increase in entropy 
(D) mechanical advantage 

Answer sheet: (C)

as well as a student model explanation and answer,

1) The question states that the lawnmower engine makes a lot of noise.
2) The question states that the lawnmower engine gets very hot.
3) Noise and heat are both forms of energy.
4) The noise and heat generated from the lawnmower are a result of the conversion of energy from the fuel to mechanical energy.

Answer: (D)

Digital Socrates gives a critique of the model-generated explanation that provides localized feedback on the most significant flaw (if any) in the explanation, suggestions to address the identified flaw, as well as a numeric rating indicating the explanation quality:

The explanation states or suggests the following:
* Main flaw (standalone statement): "The noise and heat generated from the lawnmower are a result of the conversion of energy from the fuel to mechanical energy."
* Dimension: incorrect_information

Consider these points for revising the explanation:
* General: It's important to understand the difference between the different types of energy. Mechanical energy is the energy of motion, while thermal energy is the energy of heat.
* Specific: In the case of the lawnmower, the noise and heat are not a result of the conversion of energy from the fuel to mechanical energy. The noise is a result of the vibration of the engine, while the heat is a result of the friction and combustion of the fuel.

Explanation score: 2

Remarkably, despite being orders of magnitude smaller than GPT-4, our Digital Socrates models are capable of generating critiques close to GPT-4 critiques in terms of human rating and other quantitative measures (correlation of explanation scores given and error category matches). Through quantitative and qualitative analysis, we demonstrate how Digital Socrates is useful for revealing insights about student models by examining their reasoning chains.

We invite you to try out Digital Socrates for your own application!

How to use Digital Socrates?

We provide a quick example of how you can try out Digital Socrates with just a few lines of code:

'DSCritiqueBank-V1' used below can be downloaded from our dataset page .

import json
from transformers import AutoTokenizer, AutoModelForCausalLM
# Load model and tokenizer
model_path = "allenai/digital-socrates-13b"
model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_path)

# Define input data
question = "When Dennis operates his lawnmower, he notices the engine makes a lot of noise. He also notices that the engine gets very hot. Which best describes the heat and noise generated from the lawnmower? (A) a change in phase (B) thermal expansion (C) an increase in entropy (D) mechanical advantage"
explanation = "1) The question states that the lawnmower engine makes a lot of noise.\n2) The question states that the lawnmower engine gets very hot.\n3) Noise and heat are both forms of energy.\n4) The noise and heat generated from the lawnmower are a result of the conversion of energy from the fuel to mechanical energy."
answerkey = "C"
predictedanswer = "D"

# construct prompt (Llama conventions)
with open("../DSCritiqueBank-V1/DSCB-prompts.json") as file:
    prompts = json.load(file)

system_prompt = prompts['digital_socrates_v1']['system']
user_prompt = prompts['digital_socrates_v1']['main'].replace("[[QUESTION]]", question).replace("[[EXPLANATION]]", explanation).replace("[[PREDICTEDANSWER]]", predictedanswer).replace("[[ANSWERKEY]]", answerkey)

full_prompt = f"[INST] <<SYS>>\n{system_prompt}\n<</SYS>{user_prompt} [/INST]\n\n"

# Run model
input_ids = tokenizer.encode(full_prompt, return_tensors="pt").to("cuda:0")
output = model.generate(input_ids, max_new_tokens=512, temperature=0)
res = tokenizer.batch_decode(output, skip_special_tokens=True)

Print the output:

>>> print(res[0].split("[/INST]")[-1])

The explanation states or suggests the following:
* Main flaw (standalone statement): "The noise and heat generated from the lawnmower are a result of the conversion of energy from the fuel to mechanical energy."
* Dimension: incorrect_information

Consider these points for revising the explanation:
* General: It's important to understand the difference between the different types of energy. Mechanical energy is the energy of motion, while thermal energy is the energy of heat.
* Specific: In the case of the lawnmower, the noise and heat are not a result of the conversion of energy from the fuel to mechanical energy. The noise is a result of the vibration of the engine, while the heat is a result of the friction and combustion of the fuel.

Explanation score: 2

More details about Digital Socrates ...

For more details about Digital Socrates, please refer to our:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 57.34
AI2 Reasoning Challenge (25-Shot) 58.36
HellaSwag (10-Shot) 80.14
MMLU (5-Shot) 57.01
TruthfulQA (0-shot) 44.47
Winogrande (5-shot) 74.59
GSM8k (5-shot) 29.49

Runs of allenai digital-socrates-13b on huggingface.co

1.9K
Total runs
0
24-hour runs
-12
3-day runs
-31
7-day runs
854
30-day runs

More Information About digital-socrates-13b huggingface.co Model

More digital-socrates-13b license Visit here:

https://choosealicense.com/licenses/apache-2.0

digital-socrates-13b huggingface.co

digital-socrates-13b huggingface.co is an AI model on huggingface.co that provides digital-socrates-13b's model effect (), which can be used instantly with this allenai digital-socrates-13b model. huggingface.co supports a free trial of the digital-socrates-13b model, and also provides paid use of the digital-socrates-13b. Support call digital-socrates-13b model through api, including Node.js, Python, http.

digital-socrates-13b huggingface.co Url

https://huggingface.co/allenai/digital-socrates-13b

allenai digital-socrates-13b online free

digital-socrates-13b huggingface.co is an online trial and call api platform, which integrates digital-socrates-13b's modeling effects, including api services, and provides a free online trial of digital-socrates-13b, you can try digital-socrates-13b online for free by clicking the link below.

allenai digital-socrates-13b online free url in huggingface.co:

https://huggingface.co/allenai/digital-socrates-13b

digital-socrates-13b install

digital-socrates-13b is an open source model from GitHub that offers a free installation service, and any user can find digital-socrates-13b on GitHub to install. At the same time, huggingface.co provides the effect of digital-socrates-13b install, users can directly use digital-socrates-13b installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

digital-socrates-13b install url in huggingface.co:

https://huggingface.co/allenai/digital-socrates-13b

Url of digital-socrates-13b

digital-socrates-13b huggingface.co Url

Provider of digital-socrates-13b huggingface.co

allenai
ORGANIZATIONS

Other API from allenai

huggingface.co

Total runs: 91.7K
Run Growth: 78.6K
Growth Rate: 85.70%
Updated: Outubro 18 2023
huggingface.co

Total runs: 91.3K
Run Growth: 63.3K
Growth Rate: 69.57%
Updated: Janeiro 06 2025
huggingface.co

Total runs: 77.3K
Run Growth: -517.1K
Growth Rate: -669.13%
Updated: Outubro 10 2024
huggingface.co

Total runs: 63.3K
Run Growth: 51.7K
Growth Rate: 81.63%
Updated: Outubro 10 2024
huggingface.co

Total runs: 61.6K
Run Growth: -50.5K
Growth Rate: -81.96%
Updated: Dezembro 04 2024
huggingface.co

Total runs: 23.0K
Run Growth: 7.7K
Growth Rate: 33.79%
Updated: Agosto 14 2024
huggingface.co

Total runs: 8.5K
Run Growth: 3.3K
Growth Rate: 36.78%
Updated: Julho 16 2024
huggingface.co

Total runs: 6.1K
Run Growth: -21.5K
Growth Rate: -354.06%
Updated: Julho 03 2024
huggingface.co

Total runs: 5.1K
Run Growth: -17.0K
Growth Rate: -321.48%
Updated: Julho 16 2024
huggingface.co

Total runs: 2.5K
Run Growth: -163
Growth Rate: -6.49%
Updated: Dezembro 04 2024
huggingface.co

Total runs: 1.7K
Run Growth: -110
Growth Rate: -6.43%
Updated: Julho 16 2024
huggingface.co

Total runs: 895
Run Growth: 878
Growth Rate: 98.10%
Updated: Janeiro 24 2023
huggingface.co

Total runs: 502
Run Growth: -100
Growth Rate: -21.23%
Updated: Janeiro 24 2023
huggingface.co

Total runs: 486
Run Growth: 256
Growth Rate: 52.67%
Updated: Fevereiro 12 2024
huggingface.co

Total runs: 374
Run Growth: 354
Growth Rate: 94.65%
Updated: Junho 13 2024
huggingface.co

Total runs: 313
Run Growth: -437
Growth Rate: -139.62%
Updated: Abril 30 2024
huggingface.co

Total runs: 297
Run Growth: 159
Growth Rate: 53.54%
Updated: Abril 19 2024