surfPRM
Collection
3 items • Updated
conversation listlengths 3 3 |
|---|
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
[
{
"role": "system",
"content": "You are a skilled expert at evaluating assistant responses. You should evaluate given responses based on the judging criteria.\n Given the context of the conversation and two responses from the Assistant, you need to refer to determine the better response. Provide an overall ... |
End of preview. Expand in Data Studio
surfPRM-data
SFT training data for surfPRM, a process reward model (PRM) for web agents.
- 9,821 pairwise step-preference samples stored as a single JSON array
- Each sample has one field
conversationwithsystem/user/assistantturns: the user turn contains the task intent, the current page's accessibility tree (AXTree), the previous action trajectory, the start/current URLs, and two candidate next actions; the assistant turn contains structured<State>/<Criteria>/<Analysis>/<Answer>reasoning ending in the preferred action - The exact prompt template is documented in the model cards of the models trained on this data: surfPRM-qwen3.5-4b and surfPRM-qwen3.5-9b
License
Released under Apache 2.0.
- Downloads last month
- 30