Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
Yueqi Zhang, Peiwen Yuan, Yiwei Li, Shaoxiong Feng, Xinglin Wang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
Abstract
Human-AI conversation frequently relies on quoting earlier text-"check it with the formula I just highlighted"-yet today's large language models (LLMs) lack an explicit mechanism for locating and exploiting such spans. We formalize the challenge as span-conditioned generation, decomposing each turn into the dialogue history, a set of token-offset quotation spans, and an intent utterance. Building on this abstraction, we introduce a quotation-centric data pipeline that automatically synthesizes task-specific dialogues, verifies answer correctness through multi-stage consistency checks, and yields both a heterogeneous training corpus and the first benchmark covering five representative scenarios. To meet the benchmark's zerooverhead and parameter-efficiency requirements, we propose QuAda, a lightweight training-based method that attaches two bottleneck projections to every attention head, dynamically amplifying or suppressing attention to quoted spans at inference time while leaving the prompt unchanged and updating < 2.8% of backbone weights. Experiments across models show that QuAda is suitable for all scenarios and generalizes to unseen topics, offering an effective, plug-and-play solution for quotation-aware dialogue. 1
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 on10
- Inference-Time Intervention: Eliciting Truthful Answers from a Language ModelKenneth Li, Oam Patel, Fernanda B. Viégas, Hanspeter Pfister et al.NeurIPS 2023 · 1,549 citations
- In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space SteeringSheng Liu, Haotian Ye, Lei Xing, James Y. ZouICML 2024 · 244 citations
- On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A SurveyLin Long, Rui Wang, Ruixuan Xiao, Junbo Zhao et al.ACL Findings 2024 · 131 citations
- Evaluating Open-Domain Question Answering in the Era of Large Language ModelsEhsan Kamalloo, Nouha Dziri, Charles L. A. Clarke, Davood RafieiACL 2023 · 96 citations
- Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMsQingru Zhang, Chandan Singh, Liyuan Liu, Xiaodong Liu et al.ICLR 2024 · 76 citations
Related papers
- Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code TranslationLe Chen, Nuo Xu, Winson Chen, Bin Lei et al.ACL 2026 · 6 citations
- Synthesize, Prompt and Transfer: Zero-shot Conversational Question Generation with Pre-trained Language ModelHongwei Zeng, Bifan Wei, Jun Liu, Weiping FuACL 2023 · 3 citations
- Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language ModelsYukun Huang, Sanxing Chen, Jian Pei, Manzil Zaheer et al.ICLR 2026 · 1 citation
- q2d: Turning Questions into Dialogs to Teach Models How to SearchYonatan Bitton, Shlomi Cohen-Ganor, Ido Hakimi, Yoad Lewenberg et al.EMNLP 2023 · 3 citations
- DRInQ: Evaluating Conversational Implicature with Controlled Context VariationHirona Jacqueline Arai, Xiang RenACL 2026
