Loading the SOTA2 catalog…
SOTA2 Research · tasks
Explore the problems researchers are working on and the benchmarks used to measure progress.
| Task Name | Domain | Benchmarks | Papers | Last Update |
|---|---|---|---|---|
| Aggregate Reasoning Performance | 1 | 1 | Mar 24, 2026 | |
| Structured-based Jailbreak Attack Defense | 1 | 1 | Mar 24, 2026 | |
| Perturbation-based Jailbreak Attack Defense | 1 | 1 | Mar 24, 2026 | |
| Counselor performance expert evaluation | 1 | 1 | Feb 18, 2026 | |
| Memory-Augmented Dialogue | 1 | 2 | Feb 22, 2026 | |
| Text-only Jailbreak Attack Defense | 1 | 1 | Mar 24, 2026 | |
| Reasoning Quality | 1 | 1 | Feb 18, 2026 | |
| Personalized Dialogue Response Generation |
| 1 |
| 1 |
| Feb 19, 2026 |
| LLM Pacing | 1 | 1 | Mar 25, 2026 |
|---|
| Community Alignment | 1 | 1 | Feb 19, 2026 |
|---|
| Patient profile simulation human evaluation | 1 | 1 | Mar 25, 2026 |
|---|
| Speech Generation and Interaction | 1 | 1 | Feb 19, 2026 |
|---|
| Question Answering Feedback Generation | 1 | 1 | Feb 18, 2026 |
|---|
| Descriptive Question Answering | 1 | 1 | Mar 25, 2026 |
|---|
| General Knowledge Examination | 1 | 1 | Feb 19, 2026 |
|---|
| Refusal Ablation and Jailbreak Attack Success | 1 | 1 | Mar 25, 2026 |
|---|
| Loneliness Mitigation | 1 | 1 | Mar 25, 2026 |
|---|
| Human Expert Alignment | 1 | 1 | Feb 19, 2026 |
|---|
| Loneliness Simulation | 1 | 1 | Mar 25, 2026 |
|---|
| Dialogue Utterance Re-ranking | 1 | 1 | Feb 19, 2026 |
|---|
| Long-horizon language-conditioned policy learning | 1 | 1 | Mar 25, 2026 |
|---|
| Dialogue Style Evaluation | 1 | 1 | Mar 25, 2026 |
|---|
| Refusal behavior defense | 1 | 1 | Feb 19, 2026 |
|---|
| SAE Feature Explanation Evaluation | 1 | 1 | Mar 25, 2026 |
|---|
| Checkpoint Selection | 1 | 1 | Mar 25, 2026 |
|---|