Unverified50% confidenceBenchmarkExact time
TurnTurk-GPT outperforms widely used multilingual turn-end detectors in both record-disjoint and speaker-disjoint evaluation.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/2/2026
First Seen
Valid until: 1/31/2027
Sources
Related Entities
Related Claims
UnverifiedThe first version of the evaluation used GPT-4 as a judge to read the conversation trajectory and output noticed: true/false, but it collapsed in actual use for three specific reasons: position bias in long conversations, the judge model's tendency toward charitable interpretation, and non-determinism across runs.70% similarUnverifiedThe TurnTurk-GPT model trained only on synthetic dialogue performs weakest, indicating that real dialogue data is indispensable for capturing natural turn-transition patterns.68% similarUnverifiedWhen the speaker pauses, the zero-shot baseline model and the multilingual baseline model are close to chance level, whereas TurnTurk-GPT still maintains some performance.68% similarUnverifiedTurnTurk-GPT is a text-based Turkish turn predictor, trained by fine-tuning a Turkish GPT-2 model with the TurnGPT objective.65% similarUnverifiedModern large language models (such as the GPT series) almost universally adopt a decoder-only architecture, using masked self-attention to ensure that autoregressive generation does not leak future token information.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125805API
curl https://kongchang.com/api/v1/knowledge/claims/1125805MCP
get_claim(id=1125805)