A systematic review of over 200 studies concludes that LLMs in recommender systems act as a double-edged sword, creating both opportunities and new risks for trustworthiness.
In: Proceedings of the 2020 Conference on Empirical Methods in Natu- ral Language Processing: System Demonstrations
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
SmoothLLM mitigates jailbreaking attacks on LLMs by randomly perturbing multiple copies of a prompt at the character level and aggregating the outputs to detect adversarial inputs.
Baseline defenses including perplexity-based detection, input preprocessing, and adversarial training offer partial robustness to text adversarial attacks on LLMs, with challenges arising from weak discrete optimizers.
The paper argues, without completed experiments, that zero-width Unicode steganography could be layered on top of imitation, translation, and obfuscation to evade stylometric authorship attribution.
AI researchers must lead technical research in arms control to mitigate risks from military AI systems, drawing lessons from nuclear deterrence.
citing papers explorer
-
Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges
A systematic review of over 200 studies concludes that LLMs in recommender systems act as a double-edged sword, creating both opportunities and new risks for trustworthiness.
-
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
SmoothLLM mitigates jailbreaking attacks on LLMs by randomly perturbing multiple copies of a prompt at the character level and aggregating the outputs to detect adversarial inputs.
-
Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Baseline defenses including perplexity-based detection, input preprocessing, and adversarial training offer partial robustness to text adversarial attacks on LLMs, with challenges arising from weak discrete optimizers.
-
Unveiling Unicode's Unseen Underpinnings in Undermining Authorship Attribution
The paper argues, without completed experiments, that zero-width Unicode steganography could be layered on top of imitation, translation, and obfuscation to evade stylometric authorship attribution.
-
AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks
AI researchers must lead technical research in arms control to mitigate risks from military AI systems, drawing lessons from nuclear deterrence.