REVIEW 5 cited by
Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The detection of offensive language in the context of a dialogue has become an increasingly important application of natural language processing. The detection of trolls in public forums (Gal\'an-Garc\'ia et al., 2016), and the deployment of chatbots in the public domain (Wolf et al., 2017) are two examples that show the necessity of guarding against adversarially offensive behavior on the part of humans. In this work, we develop a training scheme for a model to become robust to such human attacks by an iterative build it, break it, fix it strategy with humans and models in the loop. In detailed experiments we show this approach is considerably more robust than previous systems. Further, we show that offensive language used within a conversation critically depends on the dialogue context, and cannot be viewed as a single sentence offensive detection task as in most previous work. Our newly collected tasks and methods will be made open source and publicly available.
Forward citations
Cited by 5 Pith papers
-
CapTune: Adapting Non-Speech Captions With Anchored Generative Models
CapTune lets caption creators set bounds and viewers tune non-speech caption text; a 19-person qualitative evaluation reported greater engagement and retained creative control.
-
Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
Summaries of LLM safety papers, paired with a completion-style payload containing a harmful query, jailbreak aligned LLMs at high reported success rates and expose a defense paper versus attack paper bias.
-
Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models
QDRT combines behavior-conditioned RL, multiple specialized attackers, and a MAP-Elites replay buffer to generate LLM attacks that are more toxic and cover more risk-category/style combinations.
-
InfoFlood: Jailbreaking Large Language Models with Information Overload
InfoFlood claims near-perfect jailbreak success on four frontier LLMs by rewriting harmful queries into verbose academic prose with fake citations, past-tense framing, and ethical disclaimers, without adversarial suffixes.
-
Agentic Web: Weaving the Next Web with AI Agents
A position paper defines the Agentic Web as the next web era and proposes a three-dimensional conceptual framework for understanding and building it.
Discussion (0). Sign in to comment.