The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The paper introduces UPHELD, a large benchmark of human-to-human dialogues written by professional script writers, featuring realistic turn densities and over 36,000 per-turn human annotations. It evaluates existing automatic metrics and LLM-as-a-judge methods, finding them unreliable against expert human judgment. Using UPHELD, the authors develop a Mixture-of-Judges framework that improves correlation with human assessments by about 30%.
The paper introduces Evaluation-as-Search (EaS), a feedback‑driven method that adaptively probes LLM‑powered meeting assistants by focusing on natural questions likely to reveal grounding failures. Using EaS, the authors build MeetingProbe, a benchmark of over 3,000 annotated question‑answer pairs from 20 transcripts across three meeting genres and three assistants. Ablation studies show that adaptive search uncovers 2.5× more failures than random probing, revealing a capability gradient and eight recurring failure categories dominated by discourse‑pragmatic challenges.
arXiv:2606. 08445v1 Announce Type: cross Abstract: Meeting documents are challenging to summarize due to their length and complex conversational structure.
arXiv:2609.26780v1 Announce Type: cross Abstract: Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distingu...
arXiv:2606. 27226v1 Announce Type: new Abstract: Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug.
arXiv:2607. 12085v1 Announce Type: new Abstract: Evaluating retail conversational agents requires methods beyond lexical-overlap metrics to assess intent alignment, factuality, helpfulness, clarity, tone, and overall response quality.