Related papers: Lattice: Generative Guardrails for Conversational …
We introduce Lattice, a hybrid sequential prediction system that conditionally activates learned behavioral structure using binary confidence gating. The system clusters behavior windows into behavioral archetypes and uses binary confidence…
We introduce a lightweight yet highly effective safety guardrail framework for language models, demonstrating that small-scale language models can achieve, and even surpass, the performance of larger counterparts in content moderation…
Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning.…
Current large language models reason in isolation. Although it is common to sample multiple reasoning paths in parallel, these trajectories do not interact, and often fail in the same redundant ways. We introduce LACE, a framework that…
As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural…
Guardrails are a critical safety layer for modern AI systems, but their operating regime is changing. As LLMs are deployed as customized assistants, safety policies are increasingly specified at inference time by users, organizations, or…
Recent advances in large language models have demonstrated impressive capabilities in task-oriented applications, yet building emotionally intelligent chatbots that can engage in natural, strategic conversations remains a challenge. We…
As AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line of defense against concrete deployment harms. In these settings, guardrail failures are no…
Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions, often involving complex function calls and dynamic user-agent exchanges. Existing simulation-based data generation methods for such…
A wave of new task-based virtual assistants has been fueled by increasingly powerful large language models (LLMs), such as GPT-4 (OpenAI, 2023). A major challenge in deploying LLM-based virtual conversational assistants in real world…
Large Language Models (LLMs) have demonstrated powerful capabilities that render them valuable in different applications, including conversational AI products. It is paramount to ensure the security and reliability of these products by…
Ensuring the safety of large language models (LLMs) is critical as they are deployed in real-world applications. Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety…
Guardrails are critical for the safe deployment of Large Language Models (LLMs)-powered software. Unlike traditional rule-based systems with limited, predefined input-output spaces that inherently constrain unsafe behavior, LLMs enable…
Large language models (LLMs) have achieved remarkable success in diverse tasks, yet their safety alignment remains fragile during adaptation. Even when fine-tuning on benign data or with low-rank adaptation, pre-trained safety behaviors are…
Large language models (LLMs) have convincing performance in a variety of downstream tasks. However, these systems are prone to generating undesirable outputs such as harmful and biased text. In order to remedy such generations, the…
Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-generation autonomous cars. In this context, safety is no longer about blocking harmful…
The trend towards large language models (LLMs) for guardrailing against undesired behaviors is increasing and has shown promise for censoring user inputs. However, increased latency, memory consumption, hosting expenses and non-structured…
Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…
Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed…
In the current user-server interaction paradigm of prompted generation with large language models (LLM) on cloud, the server fully controls the generation process, which leaves zero options for users who want to keep the generated text to…