Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Spirit-LM (Expr.)

Spirit-LM (Expr.)

Reported on 8 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical8 results

Language ModellingonSALMon
Background Alignment· uses extra data· 2024-02-08
59.5
SOTA
Spirit LM: Interleaved Spoken and Written Language Model arXiv:2402.05755
Language ModellingonSALMon
Sentiment Consistency· uses extra data· 2024-02-08
73.5
SOTA
Spirit LM: Interleaved Spoken and Written Language Model arXiv:2402.05755
Language ModellingonSALMon
Background (Domain) Consistency· uses extra data· 2024-02-08
55
best: 57 (pGSLM)
Spirit LM: Interleaved Spoken and Written Language Model arXiv:2402.05755
Language ModellingonSALMon
Background (Random) Consistency· uses extra data· 2024-02-08
64
best: 66 (pGSLM)
Spirit LM: Interleaved Spoken and Written Language Model arXiv:2402.05755
Language ModellingonSALMon
Gender Consistency· uses extra data· 2024-02-08
85
best: 88.5 (pGSLM)
Spirit LM: Interleaved Spoken and Written Language Model arXiv:2402.05755
Language ModellingonSALMon
Room Consistency· uses extra data· 2024-02-08
54.5
best: 62.5 (LAST 1.3B)
Spirit LM: Interleaved Spoken and Written Language Model arXiv:2402.05755
Language ModellingonSALMon
Sentiment Alignment· uses extra data· 2024-02-08
52
best: 55.5 (pGSLM)
Spirit LM: Interleaved Spoken and Written Language Model arXiv:2402.05755
Language ModellingonSALMon
Speaker Consistency· uses extra data· 2024-02-08
81
best: 83 (pGSLM)
Spirit LM: Interleaved Spoken and Written Language Model arXiv:2402.05755