# Knowledge Attribution Causal Ablation on ECLeKTic (test)

Source: [Knowledge Attribution Causal Ablation on ECLeKTic (test)](<https://www.sota2.com/research/sota/knowledge-attribution-causal-ablation-on-eclektic-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-19T08:04:30.122Z

Evaluation of Knowledge Attribution Causal Ablation performance on the test split of the ECLeKTic dataset, measured by metrics including Ablation Success Rate and Spurious Gain Rate.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Knowledge Attribution Causal Ablation |
| Dataset (including any stated split) | ECLeKTic (test) |
| Metric | Ablation Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Ablation Success Rate](<https://www.sota2.com/research/sota/knowledge-attribution-causal-ablation-on-eclektic-test.md?metric=Ablation%20Success%20Rate>): Higher is better; unit: PERCENT.

- [Spurious Gain Rate](<https://www.sota2.com/research/sota/knowledge-attribution-causal-ablation-on-eclektic-test.md?metric=Spurious%20Gain%20Rate>): Lower is better; unit: PERCENT.

- [Rate Difference](<https://www.sota2.com/research/sota/knowledge-attribution-causal-ablation-on-eclektic-test.md?metric=Rate%20Difference>): Lower is better; unit: PERCENT.

- [Num. Q's w/ Inconsistency](<https://www.sota2.com/research/sota/knowledge-attribution-causal-ablation-on-eclektic-test.md?metric=Num.%20Q%27s%20w%2F%20Inconsistency>): Lower is better; unit: SCALAR.

- [Num. Languages](<https://www.sota2.com/research/sota/knowledge-attribution-causal-ablation-on-eclektic-test.md?metric=Num.%20Languages>): Higher is better; unit: SCALAR.

- [Num. Blacklisted Experts](<https://www.sota2.com/research/sota/knowledge-attribution-causal-ablation-on-eclektic-test.md?metric=Num.%20Blacklisted%20Experts>): Lower is better; unit: SCALAR.

- [Num. Q's w/ Experts ID'd](<https://www.sota2.com/research/sota/knowledge-attribution-causal-ablation-on-eclektic-test.md?metric=Num.%20Q%27s%20w%2F%20Experts%20ID%27d>): Higher is better; unit: SCALAR.

- [Avg. Experts ID'd per Q](<https://www.sota2.com/research/sota/knowledge-attribution-causal-ablation-on-eclektic-test.md?metric=Avg.%20Experts%20ID%27d%20per%20Q>): Higher is better; unit: SCALAR.

- [Orig. Correct Samples](<https://www.sota2.com/research/sota/knowledge-attribution-causal-ablation-on-eclektic-test.md?metric=Orig.%20Correct%20Samples>): Higher is better; unit: SCALAR.

- [Num. Q's All Incorrect](<https://www.sota2.com/research/sota/knowledge-attribution-causal-ablation-on-eclektic-test.md?metric=Num.%20Q%27s%20All%20Incorrect>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Ablation Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| XICI | 43.7 | Not recorded | 69bb82ed0636e5bf4afc18be |
| XICI | 33.2 | Not recorded | 69bb82ed0636e5bf4afc18be |
| Random Question-Shuffling (baseline) | 7.6 | Not recorded | 69bb82ed0636e5bf4afc18be |
| Random Expert Set of Same Size (baseline) | 7.5 | Not recorded | 69bb82ed0636e5bf4afc18be |
| Random Question-Shuffling (baseline) | 7 | Not recorded | 69bb82ed0636e5bf4afc18be |
| Random Expert Set of Same Size (baseline) | 6.1 | Not recorded | 69bb82ed0636e5bf4afc18be |

### XICI

Ablation Success Rate: 43.7. Result ID: 69bbadf047f34ce924a55df8.

[Reporting paper](<https://www.sota2.com/research/paper/69bb82ed0636e5bf4afc18be.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bb82ed0636e5bf4afc18be.md>)

Recorded evaluation configuration: {"Model":"GLM-4.5-Air","Details":"45 MoE layers, 5760 total routed experts","Configuration":"max 25, τ = 0.01, layers 6-40"}. This record does not assert independent reproduction.

### XICI

Ablation Success Rate: 33.2. Result ID: 69bbadf047f34ce924a55dfb.

[Reporting paper](<https://www.sota2.com/research/paper/69bb82ed0636e5bf4afc18be.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bb82ed0636e5bf4afc18be.md>)

Recorded evaluation configuration: {"Model":"Qwen3-30B-A3B-Instruct-2507","Details":"48 MoE layers, 6144 total experts","Configuration":"max 25, τ = 0.005, layers 6-42"}. This record does not assert independent reproduction.

### Random Question-Shuffling (baseline)

Ablation Success Rate: 7.6. Result ID: 69bbadf047f34ce924a55df9.

[Reporting paper](<https://www.sota2.com/research/paper/69bb82ed0636e5bf4afc18be.md>)

Recorded evaluation configuration: {"Model":"GLM-4.5-Air","Details":"45 MoE layers, 5760 total routed experts","Configuration":"max 25, τ = 0.01, layers 6-40"}. This record does not assert independent reproduction.

### Random Expert Set of Same Size (baseline)

Ablation Success Rate: 7.5. Result ID: 69bbadf047f34ce924a55dfa.

[Reporting paper](<https://www.sota2.com/research/paper/69bb82ed0636e5bf4afc18be.md>)

Recorded evaluation configuration: {"Model":"GLM-4.5-Air","Details":"45 MoE layers, 5760 total routed experts","Configuration":"max 25, τ = 0.01, layers 6-40"}. This record does not assert independent reproduction.

### Random Question-Shuffling (baseline)

Ablation Success Rate: 7. Result ID: 69bbadf047f34ce924a55dfc.

[Reporting paper](<https://www.sota2.com/research/paper/69bb82ed0636e5bf4afc18be.md>)

Recorded evaluation configuration: {"Model":"Qwen3-30B-A3B-Instruct-2507","Details":"48 MoE layers, 6144 total experts","Configuration":"max 25, τ = 0.005, layers 6-42"}. This record does not assert independent reproduction.

### Random Expert Set of Same Size (baseline)

Ablation Success Rate: 6.1. Result ID: 69bbadf047f34ce924a55dfd.

[Reporting paper](<https://www.sota2.com/research/paper/69bb82ed0636e5bf4afc18be.md>)

Recorded evaluation configuration: {"Model":"Qwen3-30B-A3B-Instruct-2507","Details":"48 MoE layers, 6144 total experts","Configuration":"max 25, τ = 0.005, layers 6-42"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
