Reading Between the Lines: The One-Sided Conversation Problem
Summary
This paper introduces the one-sided conversation problem (1SC), addressing how to reconstruct missing dialogue and generate summaries when only one speaker's turns are available in real-world settings like telemedicine and call centers. The authors evaluate prompting and finetuned models on multiple datasets, finding that access to future context and utterance length information improves reconstruction, while high-quality summaries can be generated without full dialogue reconstruction.
View Cached Full Text
Cached at: 04/20/26, 08:31 AM
# Reading Between the Lines: The One-Sided Conversation Problem Source: https://arxiv.org/abs/2511.03056 View PDF (https://arxiv.org/pdf/2511.03056) > Abstract: Conversational AI is constrained in many real-world settings where only one side of a dialogue can be recorded, such as telemedicine, call centers, and smart glasses. We formalize this as the one-sided conversation problem (1SC): inferring and learning from one side of a conversation. We study two tasks: (1) reconstructing the missing speaker's turns for real-time use cases, and (2) generating summaries from one-sided transcripts. Evaluating prompting and finetuned models on MultiWOZ, DailyDialog, and Candor with both human A/B testing and LLM-as-a-judge metrics, we find that access to one future turn and information about utterance length improves reconstruction, placeholder prompting helps to mitigate hallucination, and while large models generate promising reconstructions with prompting, smaller models require finetuning. Further, high-quality summaries can be generated without reconstructing missing turns. We present 1SC as a novel challenge and report promising results that mark a step toward privacy-aware conversational AI. ## Submission history From: Victoria Ebert [view email (https://arxiv.org/show-email/c68990da/2511.03056)] **[[v1]](https://arxiv.org/abs/2511.03056v1)** Tue, 4 Nov 2025 22:53:57 UTC (513 KB) **[v2]** Thu, 16 Apr 2026 17:48:38 UTC (9,889 KB)
Similar Articles
Synthesis and Evaluation of Long-term History-aware Medical Dialogue
This paper introduces a framework for synthesizing long-term medical dialogue datasets using LLMs, and creates MediLongChat with three benchmark tasks to evaluate healthcare agents' memory and reasoning capabilities. Experiments show that even state-of-the-art LLMs struggle with these tasks.
Robust Summarization of Doctor-Patient Conversations: TalTech Systems for the Beyond Transcription Challenge
This paper describes TalTech's systems for generating SOAP notes directly from doctor-patient conversation audio, using Voxtral models fine-tuned with supervised learning and DAPO reinforcement learning. Their submissions ranked first in both tracks of the BeTraC challenge, achieving high concept accuracy and low hallucination rates.
Synchronization and Turn-Taking in Full-Duplex Speech Dialogue Models
This paper analyzes synchronization and turn-taking dynamics in full-duplex speech dialogue models by simulating conversations between two instances of the Moshi model, measuring representational alignment via CKA and predicting turn boundaries with LSTM probes.
Modeling turn-taking with distant viewing: investigating silence thresholds in human and AI-generated discourse
This paper explores how silence thresholds in turn-taking differ between human and AI-generated discourse, using a distant viewing approach to analyze conversational patterns.
Dialogue SWE-Bench: A Benchmark for Dialogue-Driven Coding Agents
Introduces Dialogue-SWE-Bench, a benchmark for evaluating coding agents' ability to resolve software engineering problems through dialogue with a user. Proposes a persona-grounded user simulator and a schema-guided agent that improves dialogue capabilities.