Long-form interviews require models to remember what was said minutes ago while staying responsive to new information. The InterviewBot research outlines sliding windows, attention weighting, topic stores, and drift detection—tools we study when shaping our approach to extended conversations.
Extends context windows to 228 tokens with adaptive overlap, ensuring recent utterances remain salient without exceeding model limits.
Weights the previous five exchanges using recency and topical similarity scores to inform each response.
Tracks 8-16 key topics across the session, preventing repetition and enabling intentional returns to unfinished threads.
Monitors semantic deviation in real time and signals human handoff when confidence drops below threshold.
Topic repetition
Baseline
30.0%
Published result
6.7%
Interview completion
Baseline
13.3%
Published result
46.7%
Off-topic responses
Baseline
20.0%
Published result
10.0%
Diarization accuracy
Baseline
72.7%
Published result
93.6%
Agents risk repeating questions when context windows overflow or lose topical state.
Limited memory can truncate candidate rationale, reducing downstream scoring quality.
Topic drift breaks interview structure and erodes perceived fairness.
We tune sliding-window policies and utterance weighting to prioritize recent, high-signal turns.
Candidate rationales feed structured memory slots so follow-ups retain the right level of detail.
Drift detectors route ambiguous sessions for review, keeping humans in the loop when research flags risk.
Combines vector recall for key facts with chronological buffers for dialogue tone and commitments.
Captures turn-level latency, interruption rate, and acknowledgement frequency for QA dashboards.
Industry-specific topic ontologies keep conversations focused on required competencies.