data_source string | prompt list | ability string | reward_model.ground_truth string | reward_model.style string | extra_info.answer string | extra_info.correct_count int64 | extra_info.difficulty string | extra_info.index int64 | extra_info.question string | extra_info.split string | extra_info.cotanswer string | reward_model dict | extra_info dict |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) Based on the user Query, starting with \"Belief... | Product_Substitute_Identification | no | rule | no | 7 | Easy | 33,224 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer.
The steps to generate BDI reasoning process:
(1) Based on the user Query, starting with "Belief: customer believes", lis... | train | no | {
"ground_truth": "no",
"style": "rule"
} | {
"answer": "no",
"cotanswer": "no",
"index": 0,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1)... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, ... | Product_Relation_Prediction | B | rule | B | 6 | Easy | 74,230 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively.
For th... | train | B | {
"ground_truth": "B",
"style": "rule"
} | {
"answer": "B",
"cotanswer": "B",
"index": 1,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within ... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, ... | Product_Relation_Prediction | B | rule | B | 6 | Easy | 80,823 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively.
For th... | train | B | {
"ground_truth": "B",
"style": "rule"
} | {
"answer": "B",
"cotanswer": "B",
"index": 2,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within ... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, ... | Product_Relation_Prediction | A | rule | A | 7 | Easy | 57,442 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively.
For th... | train | A | {
"ground_truth": "A",
"style": "rule"
} | {
"answer": "A",
"cotanswer": "A",
"index": 3,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within ... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, ... | Product_Relation_Prediction | A | rule | A | 7 | Easy | 56,892 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively.
For th... | train | A | {
"ground_truth": "A",
"style": "rule"
} | {
"answer": "A",
"cotanswer": "A",
"index": 4,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within ... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) Based on the user Query, starting with \"Belief... | Product_Substitute_Identification | yes | rule | yes | 7 | Easy | 33,872 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer.
The steps to generate BDI reasoning process:
(1) Based on the user Query, starting with "Belief: customer believes", lis... | train | yes | {
"ground_truth": "yes",
"style": "rule"
} | {
"answer": "yes",
"cotanswer": "yes",
"index": 5,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, ... | Product_Relation_Prediction | A | rule | A | 7 | Easy | 44,962 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively.
For th... | train | A | {
"ground_truth": "A",
"style": "rule"
} | {
"answer": "A",
"cotanswer": "A",
"index": 6,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within ... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, ... | Product_Relation_Prediction | A | rule | A | 7 | Easy | 29,926 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively.
For th... | train | A | {
"ground_truth": "A",
"style": "rule"
} | {
"answer": "A",
"cotanswer": "A",
"index": 7,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within ... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) Based on the user Query, starting with \"Belief... | Multiclass_Product_Classification | B: The product is somewhat relevant. It fails to fulfill some aspects of the query but the product can be used as a functional substitute. | rule | B: The product is somewhat relevant. It fails to fulfill some aspects of the query but the product can be used as a functional substitute. | 7 | Easy | 38,299 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer.
The steps to generate BDI reasoning process:
(1) Based on the user Query, starting with "Belief: customer believes", lis... | train | B: The product is somewhat relevant. It fails to fulfill some aspects of the query but the product can be used as a functional substitute. | {
"ground_truth": "B: The product is somewhat relevant. It fails to fulfill some aspects of the query but the product can be used as a functional substitute.",
"style": "rule"
} | {
"answer": "B: The product is somewhat relevant. It fails to fulfill some aspects of the query but the product can be used as a functional substitute.",
"cotanswer": "B: The product is somewhat relevant. It fails to fulfill some aspects of the query but the product can be used as a functional substitute.",
"inde... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) Based on the user Query, starting with \"Belief... | Multiclass_Product_Classification | B: The product is somewhat relevant. It fails to fulfill some aspects of the query but the product can be used as a functional substitute. | rule | B: The product is somewhat relevant. It fails to fulfill some aspects of the query but the product can be used as a functional substitute. | 6 | Easy | 79,891 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer.
The steps to generate BDI reasoning process:
(1) Based on the user Query, starting with "Belief: customer believes", lis... | train | B: The product is somewhat relevant. It fails to fulfill some aspects of the query but the product can be used as a functional substitute. | {
"ground_truth": "B: The product is somewhat relevant. It fails to fulfill some aspects of the query but the product can be used as a functional substitute.",
"style": "rule"
} | {
"answer": "B: The product is somewhat relevant. It fails to fulfill some aspects of the query but the product can be used as a functional substitute.",
"cotanswer": "B: The product is somewhat relevant. It fails to fulfill some aspects of the query but the product can be used as a functional substitute.",
"inde... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) Based on the user Query, starting with \"Belief... | Multiclass_Product_Classification | D: The product is irrelevant to the query. | rule | D: The product is irrelevant to the query. | 7 | Easy | 32 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer.
The steps to generate BDI reasoning process:
(1) Based on the user Query, starting with "Belief: customer believes", lis... | train | D: The product is irrelevant to the query. | {
"ground_truth": "D: The product is irrelevant to the query.",
"style": "rule"
} | {
"answer": "D: The product is irrelevant to the query.",
"cotanswer": "D: The product is irrelevant to the query.",
"index": 10,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provi... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) Based on the user Purchase History, starting wi... | Sequential_Recommendation | C | rule | C | 7 | Easy | 11,726 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer.
The steps to generate BDI reasoning process:
(1) Based on the user Purchase History, starting with "Belief: customer bel... | train | C | {
"ground_truth": "C",
"style": "rule"
} | {
"answer": "C",
"cotanswer": "C",
"index": 11,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) ... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) Based on the user Query, starting with \"Belief... | Query_Product_Rank | A,B | rule | A,B | 7 | Easy | 71,574 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer.
The steps to generate BDI reasoning process:
(1) Based on the user Query, starting with "Belief: customer believes", lis... | train | A,B | {
"ground_truth": "A,B",
"style": "rule"
} | {
"answer": "A,B",
"cotanswer": "A,B",
"index": 12,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) Based on the User Review, starting with \"Belie... | Sentiment_Analysis | C: neutral | rule | C: neutral | 6 | Easy | 86,003 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer.
The steps to generate BDI reasoning process:
(1) Based on the User Review, starting with "Belief: customer believes", li... | train | C: neutral | {
"ground_truth": "C: neutral",
"style": "rule"
} | {
"answer": "C: neutral",
"cotanswer": "C: neutral",
"index": 13,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reason... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) Based on the user Query, starting with \"Belief... | Multiclass_Product_Classification | A: The product is relevant to the query, and satisfies all the query specifications. | rule | A: The product is relevant to the query, and satisfies all the query specifications. | 7 | Easy | 40,124 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer.
The steps to generate BDI reasoning process:
(1) Based on the user Query, starting with "Belief: customer believes", lis... | train | A: The product is relevant to the query, and satisfies all the query specifications. | {
"ground_truth": "A: The product is relevant to the query, and satisfies all the query specifications.",
"style": "rule"
} | {
"answer": "A: The product is relevant to the query, and satisfies all the query specifications.",
"cotanswer": "A: The product is relevant to the query, and satisfies all the query specifications.",
"index": 14,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) Based on the user Purchase History, starting wi... | Sequential_Recommendation | N | rule | N | 6 | Easy | 75,876 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer.
The steps to generate BDI reasoning process:
(1) Based on the user Purchase History, starting with "Belief: customer bel... | train | N | {
"ground_truth": "N",
"style": "rule"
} | {
"answer": "N",
"cotanswer": "N",
"index": 15,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) ... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, ... | Product_Relation_Prediction | B | rule | B | 7 | Easy | 51,081 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively.
For th... | train | B | {
"ground_truth": "B",
"style": "rule"
} | {
"answer": "B",
"cotanswer": "B",
"index": 16,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) Based on the user Query, starting with \"Belief... | Query_Product_Rank | B,A | rule | B,A | 6 | Easy | 70,240 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer.
The steps to generate BDI reasoning process:
(1) Based on the user Query, starting with "Belief: customer believes", lis... | train | B,A | {
"ground_truth": "B,A",
"style": "rule"
} | {
"answer": "B,A",
"cotanswer": "B,A",
"index": 17,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n(1) Based on the user Query, starting with \"Belief... | Query_Product_Rank | B,A | rule | B,A | 6 | Easy | 52,423 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer.
The steps to generate BDI reasoning process:
(1) Based on the user Query, starting with "Belief: customer believes", lis... | train | B,A | {
"ground_truth": "B,A",
"style": "rule"
} | {
"answer": "B,A",
"cotanswer": "B,A",
"index": 18,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. \nThe steps to generate BDI reasoning process:\n... |
ECI | [
{
"content": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, ... | Product_Relation_Prediction | B | rule | B | 6 | Easy | 26,954 | <s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively.
For th... | train | B | {
"ground_truth": "B",
"style": "rule"
} | {
"answer": "B",
"cotanswer": "B",
"index": 19,
"question": "<s>[INST] You are a helpful assistant. The assistant first thinks about the reasoning process in the mind by using Belief-Desire-Intention (BDI) framework and then provides the user with the answer. The reasoning process and answer are enclosed within... |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 3