Skip to content

Questions about Stage-1 reproduction: repeated "# Answer:" generation and lower first-stage F1 #18

Description

@pandagilr

Hi, thank you for releasing the code and models for this work.
I am trying to reproduce the Stage-1 graph-constrained reasoning model. I fine-tuned a Qwen3.5-9B model following the Stage-1 setup as closely as possible, using WebQSP + CWQ training data, index_path_length=2, group beam search with k=10, and the same output format:

Reasoning Path:

...

Answer:

...

The training itself seems to converge normally. However, during Stage-1 inference I observe a systematic generation-format problem: many candidates repeatedly generate the # Answer: marker, for example:

Answer:

Spain

Answer:

Answer:

Answer:

...

This causes very long generations, slow inference, and noticeably lower first-stage precision/F1. In my reproduced Qwen run, the first-stage recall/Hit is relatively close, but F1 is lower mainly because of noisier candidates and repeated answer markers.
I also compared this with the released/author-provided Llama3.1 Stage-1 predictions. Those predictions sometimes contain duplicate beam candidates, but they almost never show this repeated # Answer: behavior. Therefore I am trying to understand whether my reproduction differs from the original setup in decoding, tokenizer/template handling, or training target construction.
Could you please clarify the following points?

  1. Is the released Hugging Face model checkpoint exactly the same checkpoint used to generate the paper’s Stage-1 predictions, or was a local checkpoint used for the final reported numbers?
  2. Do you have any suggestions for preventing repeated # Answer: generation while keeping the original graph-constrained decoding behavior unchanged?
    Any guidance would be very helpful. I am trying to keep the reproduction as faithful as possible and would like to understand whether the discrepancy is mainly due to decoding version differences, checkpoint differences, or model-specific behavior.
    Thanks again for the great work and for releasing the resources.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions