# CallScreenBench: Benchmarking Small Language Models as Phone Secretaries

arXiv: https://arxiv.org/abs/2608.01033 · HTML: https://mlsanity.com/paper/2608.01033/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 66 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Builds on (most cited first, 30 of 42)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model](https://mlsanity.com/paper/2502.02737/) (2025)
- [VoiceBench: Benchmarking LLM-Based Voice Assistants](https://mlsanity.com/paper/2410.17196/) (2024)
- [NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets](https://mlsanity.com/paper/2104.09494/) (2021)
- [Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities](https://mlsanity.com/paper/2503.04721/) (2025)
- [ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons](https://mlsanity.com/paper/1909.03087/) (2019)
- [Voice Activity Projection: Self-supervised Learning of Turn-taking Events](https://mlsanity.com/paper/2205.09812/) (2022)
- [TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog](https://mlsanity.com/paper/2010.10874/) (2020)
- [Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics](https://mlsanity.com/paper/2503.01174/) (2025)
- [Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding](https://mlsanity.com/paper/2104.02138/) (2021)
- [Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency](https://mlsanity.com/paper/2604.04847/) (2026)
- [τ-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains](https://mlsanity.com/paper/2603.13686/) (2026)
- [URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models](https://mlsanity.com/paper/2502.17810/) (2025)
- [AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation](https://mlsanity.com/paper/2507.12705/) (2025)
- [How well are open sourced AI-generated image detection models out-of-the-box: A comprehensive benchmark study](https://mlsanity.com/paper/2602.07814/) (2026)
- [Semantic-WER: A Unified Metric for the Evaluation of ASR Transcript for End Usability](https://mlsanity.com/paper/2106.02016/) (2021)
- [MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases](https://mlsanity.com/paper/2406.10290/) (2024)
- [TTSDS -- Text-to-Speech Distribution Score](https://mlsanity.com/paper/2407.12707/) (2024)
- [SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation](https://mlsanity.com/paper/2510.14664/) (2025)
- [Combating Phone Scams with LLM-based Detection: Where Do We Stand?](https://mlsanity.com/paper/2409.11643/) (2024)

## Abstract (arXiv)

Language models small enough to run on a handset, quantized to a few bits, are increasingly capable of acting on their user's behalf -- which makes on-device task automation newly plausible. One such task is answering the phone. A phone secretary takes an unknown inbound call on its owner's behalf, and unlike the agents most benchmarks evaluate, it has no cooperative caller-assigned task to complete: the caller holds the goal and may be an adversary, while the secretary must begin deciding how to respond without an oracle. What matters is not task success but whether the owner would endorse how their proxy handled the call. We evaluate only the text-domain conversational decision layer; speech recognition, audio interaction, end-to-end latency, and handset execution are outside scope. We present CallScreenBench, which reports five automated call-and-note measure groups motivated by owner endorsement. Each is paired, where available, with a counter-metric and an uncertainty estimate; no benchmark-wide Q1-Q5 composite or leaderboard score is defined. Three guardedness diagnostics identify candidate cases for a toolless proxy that holds no credentials and calls no tools. Across three model families represented by paired 4-bit checkpoints (0.6-4B), the primary scoring snapshot gives the larger checkpoint higher point estimates on several service, recall, and plausibility measures, while triage discrimination follows a different ordering. Bare scam-side TPR rewards universal suspicion, and pairwise separation changes when legitimate-side false positives are included and across judge snapshots. Scripted degenerate agents expose further floors, including a hangup-and-echo policy with entity recall 1.000. We report quality measures and guardedness channels separately so that a single pass/fail score does not hide their trade-offs.