CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants (2024.naacl-long)
Copied to clipboard
| Challenge: | A major challenge in deploying LLM-based virtual conversational assistants in real world settings is ensuring they operate within what is admissible for the task. |
| Approach: | They propose to use large language models (LLMs) to generate training data with two key LLM components: scenario-augmented generation and contrastive training examples. |
| Outcome: | The proposed model improves over baselines in multiple dialogue domains. |
Similar Papers
Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications (2025.acl-tutorials)
Copied to clipboard
Traian Rebedea, Leon Derczynski, Shaona Ghosh, Makesh Narsimhan Sreedhar, Faeze Brahman, Liwei Jiang, Bo Li, Yulia Tsvetkov, Christopher Parisien, Yejin Choi
| Challenge: | Pretrained generative models provide novel ways for users to interact with computers. |
| Approach: | This tutorial provides an overview of key guardrail mechanisms developed for LLMs along with evaluation methodologies and a detailed security assessment protocol. |
| Outcome: | This tutorial provides an overview of key guardrail mechanisms developed for LLMs, along with evaluation methodologies and a detailed security assessment protocol. |
Peering Behind the Shield: Guardrail Identification in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Identifying guardrails in conversational AI agents is critical for identifying malicious content . identifying guardrail components in black-box AI agents poses security challenges . |
| Approach: | They propose a method that leverages guard-specific adversarial prompts to detect guardrails in black-box AI agents. |
| Outcome: | The proposed method achieves perfect classification accuracy in multiple scenarios. |
LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues (2024.naacl-srw)
Copied to clipboard
Joe Stacey, Jianpeng Cheng, John Torr, Tristan Guigue, Joris Driesen, Alexandru Coca, Mark Gaynor, Anders Johannsen
| Challenge: | Existing datasets with limited domain coverage and few challenging conversational phenomena are often unlabelled . Existing data is limited in quality and lacks a robust evaluation process . |
| Approach: | They propose a high quality data generation system that generates high quality dialogues using 4,277 conversations across 100 intents. |
| Outcome: | The proposed system produces high quality dialogue data with high quality labels. |
Diversity Helps Jailbreak Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for jailbreaking large language models rely on laborious human engineering and whitebox access to model internals. |
| Approach: | They propose a method that instructs large language models to deviate from prior context and generate harmful outputs by instructing them to deviat from previous attacks. |
| Outcome: | The proposed method achieves a 62.83% higher success rate in compromising ten leading chatbots, while using only 12.9% of the queries. |
Plan-Grounded Large Language Models for Dual Goal Conversational Settings (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing studies show that LLMs can follow user instructions, but it is unclear how they can lead a plan-grounded conversation in mixed-initiative settings where instructions flow in both directions of the conversation. |
| Approach: | They propose a dual-purpose mixed-initiative conversational setting where the LLM grounds the conversation on an arbitrary plan and seeks to satisfy both a procedural plan and user instructions. |
| Outcome: | The proposed model achieves 2.1x improvement over a strong baseline and good generalization to unseen domains. |
Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to generate toxic content by large language models are based on pipelines . current approaches focus on preserving performance while effectively mitigating toxicity . |
| Approach: | They propose a framework for implicit knowledge editing and controlled text generation by using hard negatives. |
| Outcome: | The proposed framework significantly reduces toxic generation while maintaining strong performance on downstream tasks. |
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in instruction-tuning datasets focus on specific tasks like mathematical or logical reasoning. |
| Approach: | They propose to use synthetic dialogues to help language models remain focused on the subject at hand during task-oriented interactions. |
| Outcome: | The proposed dataset improves language models' ability to maintain topical coherence compared to general-purpose instruction-tuned LLMs like gpt-4-turbo and Mixtral-Instruct. |
GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are expensive to run within a large-scale system and not ideal for low-latency use cases. |
| Approach: | They propose a pipeline that leverages Large Language Models (LLMs) for dataset augmentation. |
| Outcome: | The proposed pipeline improves the performance of a harmful text classification dataset using Large Language Models (LLMs). |
GrounDial: Human-norm Grounded Safe Dialog Response Generation (2024.findings-eacl)
Copied to clipboard
| Challenge: | Recent conversational AI systems generate unsafe responses agreeing to offensive user input or including toxic content. |
| Approach: | They propose a method where response safety is achieved by grounding responses to commonsense social rules without fine-tuning. |
| Outcome: | The proposed approach is quantitatively and qualitatively safer even without additional data or tuning. |
Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models have shown a powerful ability for text generation, but undesired behaviors such as toxicity and hallucinations can manifest. |
| Approach: | They propose to formalize text generation as a future-constrained generation problem to minimize undesirable behaviors and enforce faithfulness to instructions. |
| Outcome: | The proposed approach is effective across three tasks, including keyword-constrained generation, toxicity reduction, and factual correctness in question-answering. |