Overhaul LLM simulator: persona, RAG, student-split eval#68
Merged
Conversation
- Make grounded (real student trajectory) the only execution mode - Remove prompt_strategies.py (unused) and power_analysis.py - Remove dead functions: load_eval_items, _load_trajectory, _load_zero_shot, retrieve_examples, retrieve_context, _retrieve_self_similar, summarize_history, summarize_rag_context, SUMMARY_PROMPT - Remove early_stop_patience (unused in grounded mode)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
run.py(net -500 lines): simplified grading/evaluation looppersona.py) for behavioral simulationrag.py) for context-aware promptssummarize.py) for multi-attempt trackingprompt_strategies.py)run_student_split.py,student_split_loader.py) bridging to temporal_eval data splitsanalyze_results.py,plot_attempt_accuracy.py,power_analysis.py)data_loader.pywith temporal filtering, course params, CSV dedupprompts.pyandrunners.pyFiles changed (13)
llm_simulator/run.py— major refactorllm_simulator/prompts.py— updated prompt assemblyllm_simulator/runners.py— updated model wrappersllm_simulator/data_loader.py— temporal filtering, course paramllm_simulator/persona.py— newllm_simulator/rag.py— newllm_simulator/summarize.py— newllm_simulator/prompt_strategies.py— newllm_simulator/run_student_split.py— newllm_simulator/student_split_loader.py— newllm_simulator/analyze_results.py— newllm_simulator/plot_attempt_accuracy.py— newllm_simulator/power_analysis.py— newTest plan
python3 -c "import llm_simulator.run"— imports cleanpython3 -c "import llm_simulator.run_student_split"— imports cleanpython3 -c "import llm_simulator.persona"— imports clean