# Citation Hallucination Detection on NeuCLIR 2024 (test)

Source: [Citation Hallucination Detection on NeuCLIR 2024 (test)](<https://www.sota2.com/research/sota/citation-hallucination-detection-on-neuclir-2024-test>)

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

Data updated: 2026-02-26T05:24:52.500Z

Evaluation of model performance on citation hallucination detection using the test split of the NeuCLIR 2024 dataset.

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 | Citation Hallucination Detection |
| Dataset (including any stated split) | NeuCLIR 2024 (test) |
| Metric | AUC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 26 of 26 |
| 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

- [AUC](<https://www.sota2.com/research/sota/citation-hallucination-detection-on-neuclir-2024-test.md?metric=AUC>): Higher is better; unit: PERCENT.

- [PCC](<https://www.sota2.com/research/sota/citation-hallucination-detection-on-neuclir-2024-test.md?metric=PCC>): Higher is better; unit: SCALAR.

- [Precision](<https://www.sota2.com/research/sota/citation-hallucination-detection-on-neuclir-2024-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/citation-hallucination-detection-on-neuclir-2024-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1](<https://www.sota2.com/research/sota/citation-hallucination-detection-on-neuclir-2024-test.md?metric=F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AUC | Result date | Report paper |
| --- | --- | --- | --- |
| FACTUM | 73.7 | Not recorded | 69647fda53fdd5c3617445b8 |
| FACTUM | 73.6 | Not recorded | 69647fda53fdd5c3617445b8 |
| FACTUM | 71.5 | Not recorded | 69647fda53fdd5c3617445b8 |
| FACTUM | 70 | Not recorded | 69647fda53fdd5c3617445b8 |
| FACTUM | 69.3 | Not recorded | 69647fda53fdd5c3617445b8 |
| CAS+PFS | 68.7 | Not recorded | 69647fda53fdd5c3617445b8 |
| FACTUM | 68.2 | Not recorded | 69647fda53fdd5c3617445b8 |
| CAS+PFS | 67.7 | Not recorded | 69647fda53fdd5c3617445b8 |
| CAS+PFS | 67.6 | Not recorded | 69647fda53fdd5c3617445b8 |
| LN-Entropy | 67.1 | Not recorded | 69647fda53fdd5c3617445b8 |
| Perplexity | 67 | Not recorded | 69647fda53fdd5c3617445b8 |
| CAS+PFS | 66.8 | Not recorded | 69647fda53fdd5c3617445b8 |
| ECS+PKS | 66.8 | Not recorded | 69647fda53fdd5c3617445b8 |
| CAS+PFS | 64.5 | Not recorded | 69647fda53fdd5c3617445b8 |
| Perplexity | 63.8 | Not recorded | 69647fda53fdd5c3617445b8 |
| LN-Entropy | 63.7 | Not recorded | 69647fda53fdd5c3617445b8 |
| Energy | 61.7 | Not recorded | 69647fda53fdd5c3617445b8 |
| ECS+PKS | 61.3 | Not recorded | 69647fda53fdd5c3617445b8 |
| ECS+PKS | 61 | Not recorded | 69647fda53fdd5c3617445b8 |
| Energy | 60.6 | Not recorded | 69647fda53fdd5c3617445b8 |
| CAS+PFS | 59.2 | Not recorded | 69647fda53fdd5c3617445b8 |
| ECS+PKS | 58.8 | Not recorded | 69647fda53fdd5c3617445b8 |
| ECS+PKS | 54.9 | Not recorded | 69647fda53fdd5c3617445b8 |
| ECS+PKS | 53.6 | Not recorded | 69647fda53fdd5c3617445b8 |
| P(True) | 48.1 | Not recorded | 69647fda53fdd5c3617445b8 |
| P(True) | 48.1 | Not recorded | 69647fda53fdd5c3617445b8 |

### FACTUM

AUC: 73.7. Result ID: 6996935d5698665ec4dc981e.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"Log. Reg."}. This record does not assert independent reproduction.

### FACTUM

AUC: 73.6. Result ID: 6996935d5698665ec4dc9818.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"EBM"}. This record does not assert independent reproduction.

### FACTUM

AUC: 71.5. Result ID: 6996935d5698665ec4dc9811.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"Log. Reg."}. This record does not assert independent reproduction.

### FACTUM

AUC: 70. Result ID: 6996935d5698665ec4dc980b.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"EBM"}. This record does not assert independent reproduction.

### FACTUM

AUC: 69.3. Result ID: 6996935d5698665ec4dc981b.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"LightGBM"}. This record does not assert independent reproduction.

### CAS+PFS

AUC: 68.7. Result ID: 6996935d5698665ec4dc9817.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"EBM"}. This record does not assert independent reproduction.

### FACTUM

AUC: 68.2. Result ID: 6996935d5698665ec4dc980e.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"LightGBM"}. This record does not assert independent reproduction.

### CAS+PFS

AUC: 67.7. Result ID: 6996935d5698665ec4dc981d.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"Log. Reg."}. This record does not assert independent reproduction.

### CAS+PFS

AUC: 67.6. Result ID: 6996935d5698665ec4dc9810.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"Log. Reg."}. This record does not assert independent reproduction.

### LN-Entropy

AUC: 67.1. Result ID: 6996935d5698665ec4dc9813.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa694d1e209131cea21611.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"Classifier-free"}. This record does not assert independent reproduction.

### Perplexity

AUC: 67. Result ID: 6996935d5698665ec4dc9812.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ae51e209131cea85bd0.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"Classifier-free"}. This record does not assert independent reproduction.

### CAS+PFS

AUC: 66.8. Result ID: 6996935d5698665ec4dc980a.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"EBM"}. This record does not assert independent reproduction.

### ECS+PKS

AUC: 66.8. Result ID: 6996935d5698665ec4dc980f.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e634.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"Log. Reg."}. This record does not assert independent reproduction.

### CAS+PFS

AUC: 64.5. Result ID: 6996935d5698665ec4dc980d.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"LightGBM"}. This record does not assert independent reproduction.

### Perplexity

AUC: 63.8. Result ID: 6996935d5698665ec4dc9805.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ae51e209131cea85bd0.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"Classifier-free"}. This record does not assert independent reproduction.

### LN-Entropy

AUC: 63.7. Result ID: 6996935d5698665ec4dc9806.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa694d1e209131cea21611.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"Classifier-free"}. This record does not assert independent reproduction.

### Energy

AUC: 61.7. Result ID: 6996935d5698665ec4dc9814.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cc1e209131cea24242.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"Classifier-free"}. This record does not assert independent reproduction.

### ECS+PKS

AUC: 61.3. Result ID: 6996935d5698665ec4dc9816.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e634.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"EBM"}. This record does not assert independent reproduction.

### ECS+PKS

AUC: 61. Result ID: 6996935d5698665ec4dc9809.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e634.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"EBM"}. This record does not assert independent reproduction.

### Energy

AUC: 60.6. Result ID: 6996935d5698665ec4dc9807.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cc1e209131cea24242.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"Classifier-free"}. This record does not assert independent reproduction.

### CAS+PFS

AUC: 59.2. Result ID: 6996935d5698665ec4dc981a.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"LightGBM"}. This record does not assert independent reproduction.

### ECS+PKS

AUC: 58.8. Result ID: 6996935d5698665ec4dc980c.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e634.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"LightGBM"}. This record does not assert independent reproduction.

### ECS+PKS

AUC: 54.9. Result ID: 6996935d5698665ec4dc9819.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e634.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"LightGBM"}. This record does not assert independent reproduction.

### ECS+PKS

AUC: 53.6. Result ID: 6996935d5698665ec4dc981c.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76ad1e209131cea6e634.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"Log. Reg."}. This record does not assert independent reproduction.

### P(True)

AUC: 48.1. Result ID: 6996935d5698665ec4dc9808.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Classifier":"Classifier-free"}. This record does not assert independent reproduction.

### P(True)

AUC: 48.1. Result ID: 6996935d5698665ec4dc9815.

[Reporting paper](<https://www.sota2.com/research/paper/69647fda53fdd5c3617445b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6df71e209131cea3d034.md>)

Recorded evaluation configuration: {"Base Model":"Llama-3.1-8B-Instruct","Classifier":"Classifier-free"}. This record does not assert independent reproduction.

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