# Event Causal Identification on EventStoryLine Document-level (inter-sentence event pairs)

Source: [Event Causal Identification on EventStoryLine Document-level (inter-sentence event pairs)](<https://www.sota2.com/research/sota/event-causal-identification-on-eventstoryline-document-level-inter-sentence-event-pairs>)

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

Data updated: 2026-04-15T09:42:47.015Z

Evaluation of Event Causal Identification performance on the EventStoryLine dataset, specifically focusing on document-level inter-sentence event pairs, measured using CHR and mAcc.

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 | Event Causal Identification |
| Dataset (including any stated split) | EventStoryLine Document-level (inter-sentence event pairs) |
| Metric | CHR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [CHR](<https://www.sota2.com/research/sota/event-causal-identification-on-eventstoryline-document-level-inter-sentence-event-pairs.md?metric=CHR>): Higher is better; unit: PERCENT.

- [mAcc](<https://www.sota2.com/research/sota/event-causal-identification-on-eventstoryline-document-level-inter-sentence-event-pairs.md?metric=mAcc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | CHR | Result date | Report paper |
| --- | --- | --- | --- |
| Llama3.2-1B | 93.94 | Not recorded | 69df1bbe7d0172140ec7bb0d |
| Qwen2.5-1.5B | 54.52 | Not recorded | 69df1bbe7d0172140ec7bb0d |
| Llama3.2-1B | 4.51 | Not recorded | 69df1bbe7d0172140ec7bb0d |
| Qwen2.5-1.5B | 1.41 | Not recorded | 69df1bbe7d0172140ec7bb0d |

### Llama3.2-1B

CHR: 93.94. Result ID: 69df5d5a47f34ce924c87f5b.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bbe7d0172140ec7bb0d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bbe7d0172140ec7bb0d.md>)

Recorded evaluation configuration: {"Fine-tuning Protocol":"Vanilla (without any fine-tuning)"}. This record does not assert independent reproduction.

### Qwen2.5-1.5B

CHR: 54.52. Result ID: 69df5d5a47f34ce924c87f59.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bbe7d0172140ec7bb0d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bbe7d0172140ec7bb0d.md>)

Recorded evaluation configuration: {"Fine-tuning Protocol":"Vanilla (without any fine-tuning)"}. This record does not assert independent reproduction.

### Llama3.2-1B

CHR: 4.51. Result ID: 69df5d5a47f34ce924c87f5c.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bbe7d0172140ec7bb0d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bbe7d0172140ec7bb0d.md>)

Recorded evaluation configuration: {"Fine-tuning Protocol":"Our (fine-tuned using the CoT trace data)"}. This record does not assert independent reproduction.

### Qwen2.5-1.5B

CHR: 1.41. Result ID: 69df5d5a47f34ce924c87f5a.

[Reporting paper](<https://www.sota2.com/research/paper/69df1bbe7d0172140ec7bb0d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69df1bbe7d0172140ec7bb0d.md>)

Recorded evaluation configuration: {"Fine-tuning Protocol":"Our (fine-tuned using the CoT trace data)"}. This record does not assert independent reproduction.

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