We lifted 9 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| veronica320/faithful-cot | canonical | 8 of 9 |
| Function | Status | Where it lives |
|---|---|---|
| extract_gold_answer | Ran | veronica320/faithful-cot/source/dataset/utils.py code served (permissive licence) · get_code("f10320e98057847d") |
| is_correct | Ran | veronica320/faithful-cot/source/evaluate/evaluate_answer_acc.py code served (permissive licence) · get_code("26a0c594eb40f371") |
| lcm | Ran | veronica320/faithful-cot/source/scratch.py code served (permissive licence) · get_code("2410baeb6a8ae747") |
| load_data | Ran | veronica320/faithful-cot/source/dataset/utils.py code served (permissive licence) · get_code("1298973dba46c252") |
| solve_it | Ran | veronica320/faithful-cot/source/scratch.py code served (permissive licence) · get_code("a495f91be279d500") |
| solve_mwp | Ran | veronica320/faithful-cot/source/model/solver/MWP/math_solver.py code served (permissive licence) · get_code("913ed052cb272f34") |
| str2num | Ran | veronica320/faithful-cot/source/dataset/utils.py code served (permissive licence) · get_code("6fd802abadc37bc8") |
| timeout | Ran | veronica320/faithful-cot/source/model/codex.py code served (permissive licence) · get_code("cf46a2fecbc874d2") |
| solve | Not yet run | veronica320/faithful-cot/source/model/solver/CLUTRR/CLUTRR_solver.py code served (permissive licence) · get_code("09e91d6ca5d39a6d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
While Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of complex reasoning tasks, the generated reasoning chain does not necessarily reflect how the model arrives at the answer (aka. faithfulness). We propose Faithful CoT, a reasoning framework involving two stages: Translation (Natural Language query $\rightarrow$ symbolic reasoning chain) and Problem Solving (reasoning chain $\rightarrow$ answer), using an LM and a deterministic solver respectively. This guarantees that the reasoning chain provides a faithful explanation of the final answer. Aside from interpretability, Faithful CoT also improves empirical performance: it outperforms standard CoT on 9 of 10 benchmarks from 4 diverse domains, with a relative accuracy gain of 6.3% on Math Word Problems (MWP), 3.4% on Planning, 5.5% on Multi-hop Question Answering (QA), and 21.4% on Relational Inference. Furthermore, with GPT-4 and Codex, it sets the new state-of-the-art few-shot performance on 7 datasets (with 95.0+ accuracy on 6 of them), showing a strong synergy between faithfulness and accuracy.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2301.13379")
get_code_for_paper("2301.13379")
have("2301.13379")
Connect an agent — have() is free.