TamingLLM

Next iteration of this workshop series is to be held at ICLR 2024. Checkout LLM Agents

The proceedings of the workshop will be published by the ACL Anthology. We eagerly anticipate your valuable contributions and look forward to seeing you there!

Topics of interest include, but are not limited to:

• Alignment: Investigating techniques to better align LLMs with human values and intentions, including reward modeling, human-in-the-loop systems, and quantifying alignment metrics. Understanding the objectives pursued by a model and aligning them with human preferences are key challenges.
• In-context Learning: Exploring the role of context in LLMs, including how to improve context understanding, manage context drift, and enhance context-aware responses.
• Instruction-based Control: Comparing popular controlling mechanisms, including approaches such as logit manipulation, decoder mixing, and classifier guidance, amongst others, against the simpler instruction-based control.
• Generality: Investigating controllable techniques that work cross-task and dataset.
• Safety and Robustness: Assessing potential risks and vulnerabilities in LLMs, along with solutions such as adversarial training, safe exploration, and monitoring model behavior during deployment.
• Controllability vs. Robustness: Developing methods to better understand LLMs' decision-making processes, and how it acts in grounded scenarios. Understanding its reliance on implicit vs. explicit memory.
• Scalability and efficiency: Investigating novel approaches for reducing computational requirements for achieving control in LLMs.

The TamingLLM Workshop will be co-located with SIGDial 2023 and INLG 2023! We look forward to your participation in this exciting workshop!