RRDA introduces a router plus separate edit and locality adapters for memory-assisted knowledge editing, reporting highest accuracy on CounterFact, ZsRE, and MQuAKE-CF across two 8B models.
Canonical reference
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Lan- guage Processing
Canonical reference. 100% of citing Pith papers cite this work as background.
10
Pith papers citing it
Background
100% of classified citations
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
MemPoison enables stealthy memory poisoning in LLM agents via dialogue by using semantic relational bridges, entity masquerading, and joint embedding optimization to bypass selective extraction and rewriting, achieving up to 0.95 attack success rate.
A teacher-student reward model learns reasoning-conditioned score distributions for text-to-image images, yielding ~89% preference accuracy and a 41% net human-preference gain when used for generator optimization.
QD-LLM applies neuroevolution to prompt embeddings within a quality-diversity framework, producing 46% higher coverage and 41% higher QD-score than QDAIF on HumanEval, MBPP, and creative writing benchmarks.
NvRec profiles multiple API recommendation models on tail-API performance and applies majority voting with reliability filters to raise true accept rates while controlling rejection of uncertain outputs.
Symbolic guardrails enforce about 74% of agent security and safety requirements on three benchmarks with mostly simple checks, improving safety without sacrificing utility.
UNICS pre-trains on a pseudocode dataset for cross-lingual logic then applies multi-task transfer learning with hard-positive mining and dynamic hard-negative sampling to reach claimed SOTA on multilingual code-search benchmarks.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
CTT is a compression pipeline for LLMs that achieves up to 49x memory reduction, 10x faster inference, 81% lower CO2 emissions, and retains 68-98% accuracy on code clone detection, summarization, and generation tasks.
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
citing papers explorer
-
When to Write and When to Suppress: Route-Specialized Dual Adapters for Memory-Assisted Knowledge Editing
RRDA introduces a router plus separate edit and locality adapters for memory-assisted knowledge editing, reporting highest accuracy on CounterFact, ZsRE, and MQuAKE-CF across two 8B models.
-
Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
MemPoison enables stealthy memory poisoning in LLM agents via dialogue by using semantic relational bridges, entity masquerading, and joint embedding optimization to bypass selective extraction and rewriting, achieving up to 0.95 attack success rate.
-
Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions
A teacher-student reward model learns reasoning-conditioned score distributions for text-to-image images, yielding ~89% preference accuracy and a 41% net human-preference gain when used for generator optimization.
-
Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
QD-LLM applies neuroevolution to prompt embeddings within a quality-diversity framework, producing 46% higher coverage and 41% higher QD-score than QDAIF on HumanEval, MBPP, and creative writing benchmarks.
-
Tail-aware N-version Machine Learning Models for Reliable API Recommendation
NvRec profiles multiple API recommendation models on tail-API performance and applies majority voting with reliability filters to raise true accept rates while controlling rejection of uncertain outputs.
-
Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents
Symbolic guardrails enforce about 74% of agent security and safety requirements on three benchmarks with mostly simple checks, improving safety without sacrificing utility.
-
UNICS: Multilingual Code Search via Unified Pseudocode and Contrastive Transfer Learning
UNICS pre-trains on a pseudocode dataset for cross-lingual logic then applies multi-task transfer learning with hard-positive mining and dynamic hard-negative sampling to reach claimed SOTA on multilingual code-search benchmarks.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
Carbon-Taxed Transformers: A Green Compression Pipeline for Overgrown Language Models
CTT is a compression pipeline for LLMs that achieves up to 49x memory reduction, 10x faster inference, 81% lower CO2 emissions, and retains 68-98% accuracy on code clone detection, summarization, and generation tasks.
-
AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.