Reasoning Quality Correlation Analysis on LIAR
0.2769Somers' DMarODE(αβ)
Evaluation Results
| Method | Links | |
|---|---|---|
| MarODE(αβ)Prompting Shots=4-shot2026.03 | 0.2769 | |
| MarODE(αβ)Prompting Shots=1-shot2026.03 | 0.2762 | |
| MarODE(αβ)Prompting Shots=2-shot2026.03 | 0.2743 | |
| MarODEPrompting Shots=2-shot2026.03 | 0.2636 | |
| MarODEPrompting Shots=1-shot2026.03 | 0.2618 | |
| MarODEPrompting Shots=4-shot2026.03 | 0.2604 | |
| MarODE(αγ)Prompting Shots=2-shot2026.03 | 0.256 | |
| MarODE(αγ)Prompting Shots=1-shot2026.03 | 0.255 | |
| MarODE(αγ)Prompting Shots=4-shot2026.03 | 0.2527 | |
| MarODE_COHERENCE(α)Prompting Shots=4-shot2026.03 | 0.2427 | |
| MarODE_COHERENCE(α)Prompting Shots=1-shot2026.03 | 0.2395 | |
| MarODE_COHERENCE(α)Prompting Shots=2-shot2026.03 | 0.2357 | |
| MarODE(βγ)Prompting Shots=2-shot2026.03 | 0.2164 | |
| MarODE(βγ)Prompting Shots=4-shot2026.03 | 0.2129 | |
| MarODE_EVIDENCE(γ)Prompting Shots=2-shot2026.03 | 0.2122 | |
| MarODE(βγ)Prompting Shots=1-shot2026.03 | 0.2103 | |
| MarODE_EVIDENCE(γ)Prompting Shots=4-shot2026.03 | 0.2082 | |
| MarODE_EVIDENCE(γ)Prompting Shots=1-shot2026.03 | 0.2075 | |
| ROSCOE-SSPrompting Shots=4-shot2026.03 | 0.1386 | |
| ROSCOE-SSPrompting Shots=1-shot2026.03 | 0.1167 | |
| ROSCOE-SSPrompting Shots=2-shot2026.03 | 0.1146 | |
| ROSCOE-SAPrompting Shots=4-shot2026.03 | 0.1075 | |
| ROSCOE-SAPrompting Shots=1-shot2026.03 | 0.1004 | |
| ROSCOE-SAPrompting Shots=2-shot2026.03 | 0.0983 | |
| ROSCOE_MEANPrompting Shots=4-shot2026.03 | 0.0776 | |
| ROSCOE_MEANPrompting Shots=2-shot2026.03 | 0.0728 | |
| ROSCOE_MEANPrompting Shots=1-shot2026.03 | 0.0691 | |
| Local_and_GlobalPrompting Shots=1-shot2026.03 | 0.0417 | |
| Local_and_GlobalPrompting Shots=2-shot2026.03 | 0.0397 | |
| LLM_as_a_JudgePrompting Shots=1-shot2026.03 | 0.0367 | |
| MarODE_QUALITY(β)Prompting Shots=4-shot2026.03 | 0.0358 | |
| Local_and_GlobalPrompting Shots=4-shot2026.03 | 0.0347 | |
| MarODE_QUALITY(β)Prompting Shots=2-shot2026.03 | 0.0342 | |
| ROSCOE-LIPrompting Shots=4-shot2026.03 | 0.0286 | |
| LLM_as_a_JudgePrompting Shots=2-shot2026.03 | 0.0282 | |
| ROSCOE-LIPrompting Shots=2-shot2026.03 | 0.0279 | |
| ROSCOE-LIPrompting Shots=1-shot2026.03 | 0.0253 | |
| ReCEvalPrompting Shots=4-shot2026.03 | 0.0211 | |
| MarODE_QUALITY(β)Prompting Shots=1-shot2026.03 | 0.0181 | |
| LLM_as_a_JudgePrompting Shots=4-shot2026.03 | 0.014 | |
| ReCEvalPrompting Shots=2-shot2026.03 | 0.0084 | |
| ReCEvalPrompting Shots=1-shot2026.03 | 0.0082 | |
| ROSCOE-LCPrompting Shots=1-shot2026.03 | -0.0073 | |
| ROSCOE-LCPrompting Shots=2-shot2026.03 | -0.0076 | |
| ROSCOE-LCPrompting Shots=4-shot2026.03 | -0.0184 |