ACL Findings2026
Reading Between the Lines: The One-Sided Conversation Problem
Victoria Ebert, Rishabh Singh, Tuochao Chen, Noah A. Smith, Shyamnath Gollakota
Abstract
Conversational AI is constrained in many realworld settings where only one side of a dialogue can be recorded. We formalize the onesided conversation problem (1SC): inferring and learning from only one side of a conversation. We study two tasks: (1) reconstructing the missing speaker's turns and ( 2) generating summaries from one-sided transcripts. Evaluating models on MultiWOZ, DailyDialog, Spo-kenWOZ and Candor with both human A/B testing and LLM-as-a-judge metrics, we find that additional context improves reconstruction, 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on19
- CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and GenerationYue Wang, Weishi Wang, Shafiq R. Joty, Steven C. H. HoiEMNLP 2021 · 1,224 citations
- A Simple Language Model for Task-Oriented DialogueEhsan Hosseini-Asl, Bryan McCann, Chien-Sheng Wu, Semih Yavuz et al.NeurIPS 2020 · 590 citations
- Prometheus: Inducing Fine-Grained Evaluation Capability in Language ModelsSeungone Kim, Jamin Shin, Yejin Choi, Joel Jang et al.ICLR 2024 · 468 citations
- InCoder: A Generative Model for Code Infilling and SynthesisDaniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang et al.ICLR 2023 · 140 citations
- Exploring User Expectations of Proactive AI SystemsChristian Meurisch, Cristina A. Mihale-Wilson, Adrian Hawlitschek, Florian Giger et al.UbiComp 2021 · 66 citations
Related papers
- Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State TrackingJamin Shin, Hangyeol Yu, Hyeongdon Moon, Andrea Madotto et al.ACL Findings 2022 · 26 citations
- Narrate Dialogues for Better SummarizationRuochen Xu, Chenguang Zhu, Michael ZengEMNLP Findings 2022 · 5 citations
- Few-shot Natural Language Generation for Task-Oriented DialogBaolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li et al.EMNLP Findings 2020 · 164 citations
- MT-OSC: Path for LLMs that Get Lost in Multi-Turn ConversationJyotika Singh, Fang Tu, Miguel Ballesteros, Weiyi Sun et al.ACL Findings 2026
- PoSum-Bench: Benchmarking Position Bias in LLM-based Conversational SummarizationXu Sun, Lionel Delphin-Poulat, Christèle Tarnec, Anastasia ShimorinaEMNLP 2025 · 5 citations
