EMNLP Findings2024
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues
Makesh Narsimhan Sreedhar, Traian Rebedea, Shaona Ghosh, Jiaqi Zeng, Christopher Parisien
Abstract
Recent advancements in instruction-tuning datasets have predominantly focused on specific tasks like mathematical or logical reasoning. There has been a notable gap in data designed for aligning language models to maintain topic relevance in conversations -a critical aspect for deploying chatbots to production. We introduce the CANTTALKABOUT-THIS dataset to help language models remain focused on the subject at hand during taskoriented interactions. It consists of synthetic dialogues on a wide range of conversation topics from different domains. These dialogues are interspersed with distractor turns that intentionally divert the chatbot from the predefined topic. Fine-tuning language models on this dataset helps make them resilient to deviating from the assigned role and improves their ability to maintain topical coherence compared to generalpurpose instruction-tuned LLMs like GPT-4-TURBO and MIXTRAL-INSTRUCT. Additionally, preliminary observations suggest that training models on this dataset also enhance their performance on fine-grained instruction following tasks, including safety alignment.
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.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- The Flan Collection: Designing Data and Methods for Effective Instruction Tuning cites LoRA: Low-Rank Adaptation of Large Language Models
- The Flan Collection: Designing Data and Methods for Effective Instruction Tuning cites Measuring Massive Multitask Language Understanding
- The Flan Collection: Designing Data and Methods for Effective Instruction Tuning cites Training language models to follow instructions with human feedback
- LIMA: Less Is More for Alignment cites Training language models to follow instructions with human feedback
Cited by top-tier papers1
Builds on12
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Measuring Massive Multitask Language UnderstandingDan Hendrycks, Collin Burns, Steven Basart, Andy Zou et al.ICLR 2021 · 7,905 citations
- LIMA: Less Is More for AlignmentChunting Zhou, Pengfei Liu, Puxin Xu, Srinivasan Iyer et al.NeurIPS 2023 · 1,486 citations
- The Flan Collection: Designing Data and Methods for Effective Instruction TuningShayne Longpre, Le Hou, Tu Vu, Albert Webson et al.ICML 2023 · 908 citations
Related papers
- LoCt-Instruct: An Automatic Pipeline for Constructing Datasets of Logical Continuous InstructionsHongyu Sun, Yusuke Sakai, Haruki Sakajo, Shintaro Ozaki et al.EMNLP 2025
- Understanding Catastrophic Forgetting in Language Models via Implicit InferenceSuhas Kotha, Jacob Mitchell Springer, Aditi RaghunathanICLR 2024 · 131 citations
- Unveiling Imitation Learning: Exploring the impact of Data Falsity to Large Language ModelHyunsoo ChoACL Findings 2024
- Enhancing Chat Language Models by Scaling High-quality Instructional ConversationsNing Ding, Yulin Chen, Bokai Xu, Yujia Qin et al.EMNLP 2023 · 95 citations
- Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt TemplatesKaifeng Lyu, Haoyu Zhao, Xinran Gu, Dingli Yu et al.NeurIPS 2024 · 131 citations
