lm-sys / lm-sys/FastChat

Delayed Response

Open
#3,676 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

When comparing a reasoning model with a non-reasoning model, disable streaming, and post both responses to the user at the same time after both of the models are done to prevent the user from using model response times (ie longer response time = some sort of reasoning model) to bias voting.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing FastChat's model-comparison response handling and streaming behavior. Confirm that streaming is disabled for these comparisons and that both completed responses are posted together, so response duration does not reveal which model uses reasoning.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.