# Text Generation on DomainBench Finance

Source: [Text Generation on DomainBench Finance](<https://www.sota2.com/research/sota/text-generation-on-domainbench-finance>)

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

Data updated: 2026-04-16T07:43:17.764Z

Evaluation of text generation models on the DomainBench Finance dataset, reporting standard metrics such as BERTScore, BLEURT, BLEU, and ROUGE scores.

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 | Text Generation |
| Dataset (including any stated split) | DomainBench Finance |
| Metric | BERTScore |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [BERTScore](<https://www.sota2.com/research/sota/text-generation-on-domainbench-finance.md?metric=BERTScore>): Higher is better; unit: SCALAR.

- [BLEURT](<https://www.sota2.com/research/sota/text-generation-on-domainbench-finance.md?metric=BLEURT>): Higher is better; unit: SCALAR.

- [BLEU](<https://www.sota2.com/research/sota/text-generation-on-domainbench-finance.md?metric=BLEU>): Higher is better; unit: PERCENT.

- [ROUGE-1](<https://www.sota2.com/research/sota/text-generation-on-domainbench-finance.md?metric=ROUGE-1>): Higher is better; unit: PERCENT.

- [ROUGE-2](<https://www.sota2.com/research/sota/text-generation-on-domainbench-finance.md?metric=ROUGE-2>): Higher is better; unit: PERCENT.

- [ROUGE-L](<https://www.sota2.com/research/sota/text-generation-on-domainbench-finance.md?metric=ROUGE-L>): Higher is better; unit: PERCENT.

## Recorded results

| Method | BERTScore | Result date | Report paper |
| --- | --- | --- | --- |
| TF-TTCL | 0.7235 | Not recorded | 69e06d257d0172140ec7cb83 |
| TF-TTCL | 0.7164 | Not recorded | 69e06d257d0172140ec7cb83 |
| Deepseek-V3.2 | 0.7163 | Not recorded | 69e06d257d0172140ec7cb83 |
| Qwen-Plus | 0.7156 | Not recorded | 69e06d257d0172140ec7cb83 |
| Chain of Thoughts | 0.7115 | Not recorded | 69e06d257d0172140ec7cb83 |
| TF-TTCL | 0.7094 | Not recorded | 69e06d257d0172140ec7cb83 |
| Chain of Thoughts | 0.7002 | Not recorded | 69e06d257d0172140ec7cb83 |
| Tent | 0.6859 | Not recorded | 69e06d257d0172140ec7cb83 |
| TLM | 0.682 | Not recorded | 69e06d257d0172140ec7cb83 |
| TF-GRPO | 0.6818 | Not recorded | 69e06d257d0172140ec7cb83 |
| Llama-3.1-8B-Instruct | 0.6806 | Not recorded | 69e06d257d0172140ec7cb83 |
| EATA | 0.6792 | Not recorded | 69e06d257d0172140ec7cb83 |
| TF-GRPO | 0.6756 | Not recorded | 69e06d257d0172140ec7cb83 |
| TF-GRPO | 0.6607 | Not recorded | 69e06d257d0172140ec7cb83 |
| COME | 0.5331 | Not recorded | 69e06d257d0172140ec7cb83 |

### TF-TTCL

BERTScore: 0.7235. Result ID: 69e0928747f34ce924c98a7d.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

Recorded evaluation configuration: {"Base Model":"Deepseek-V3.2","Strategy":"TF-TTCL"}. This record does not assert independent reproduction.

### TF-TTCL

BERTScore: 0.7164. Result ID: 69e0928747f34ce924c98a79.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

Recorded evaluation configuration: {"Base Model":"Qwen-Plus","Strategy":"TF-TTCL"}. This record does not assert independent reproduction.

### Deepseek-V3.2

BERTScore: 0.7163. Result ID: 69e0928747f34ce924c98a7a.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692fc410d6b0dd33429332f4.md>)

Recorded evaluation configuration: {"Base Model":"Deepseek-V3.2","Strategy":"Standard Prompting"}. This record does not assert independent reproduction.

### Qwen-Plus

BERTScore: 0.7156. Result ID: 69e0928747f34ce924c98a76.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Base Model":"Qwen-Plus","Strategy":"Standard Prompting"}. This record does not assert independent reproduction.

### Chain of Thoughts

BERTScore: 0.7115. Result ID: 69e0928747f34ce924c98a7b.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Base Model":"Deepseek-V3.2","Strategy":"Chain of Thoughts"}. This record does not assert independent reproduction.

### TF-TTCL

BERTScore: 0.7094. Result ID: 69e0928747f34ce924c98a92.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Chain of Thoughts

BERTScore: 0.7002. Result ID: 69e0928747f34ce924c98a77.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Base Model":"Qwen-Plus","Strategy":"Chain of Thoughts"}. This record does not assert independent reproduction.

### Tent

BERTScore: 0.6859. Result ID: 69e0928747f34ce924c98a8d.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69941e209131cea22d2b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TLM

BERTScore: 0.682. Result ID: 69e0928747f34ce924c98a90.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78df1e209131cea7af13.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TF-GRPO

BERTScore: 0.6818. Result ID: 69e0928747f34ce924c98a78.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c071e209131cea8bf94.md>)

[Implementation](<https://github.com/TencentCloudADP/youtu-agent/tree/training_free_GRPO>)

Recorded evaluation configuration: {"Base Model":"Qwen-Plus","Strategy":"TF-GRPO"}. This record does not assert independent reproduction.

### Llama-3.1-8B-Instruct

BERTScore: 0.6806. Result ID: 69e0928747f34ce924c98a8c.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"status":"Base Model"}. This record does not assert independent reproduction.

### EATA

BERTScore: 0.6792. Result ID: 69e0928747f34ce924c98a8e.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea35123.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TF-GRPO

BERTScore: 0.6756. Result ID: 69e0928747f34ce924c98a7c.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c071e209131cea8bf94.md>)

[Implementation](<https://github.com/TencentCloudADP/youtu-agent/tree/training_free_GRPO>)

Recorded evaluation configuration: {"Base Model":"Deepseek-V3.2","Strategy":"TF-GRPO"}. This record does not assert independent reproduction.

### TF-GRPO

BERTScore: 0.6607. Result ID: 69e0928747f34ce924c98a91.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c071e209131cea8bf94.md>)

[Implementation](<https://github.com/TencentCloudADP/youtu-agent/tree/training_free_GRPO>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### COME

BERTScore: 0.5331. Result ID: 69e0928747f34ce924c98a8f.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d257d0172140ec7cb83.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75331e209131cea665c8.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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