PhantomBench is a new benchmark of 60K+ non-existent terms showing language models hallucinate at rates up to 86.7 percent even when inputs assume the concepts exist.
R -Tuning: Instructing Large Language Models to Say ` I Don ' t Know'
8 Pith papers cite this work, alongside 16 external citations. Polarity classification is still indexing.
8
Pith papers citing it
16
external citations · OpenAlex
verdicts
UNVERDICTED 8representative citing papers
Luar is a reinforcement learning method enabling reasoning language models to decide when to invoke English translation for improved multilingual reasoning.
A distribution-free abstention rule grounded in multiple hypothesis testing uses execution consistency to let code LLMs avoid hallucination-prone tasks with theoretical guarantees.
KARL uses a knowledge-boundary-aware reward from within-group response statistics and two-stage RL training to align LLM abstention with actual knowledge, yielding a better accuracy-hallucination trade-off on benchmarks.
LoVeC uses RL to train LLMs to output verbalized numerical confidence scores for statements in long-form text, achieving better calibration than self-consistency baselines on QA datasets while being 20x faster.
LLMs trained via rubric-based self-rewarding RL with GRPO enhanced feeling expression and sycophancy robustness but degraded truthful QA performance.
Exploration-Commitment Decoupling instantiated as Calibration-Aware Generation improves long-form factuality by up to 13% and reduces decoding time by up to 37% on five benchmarks.
Hybrid entropy-uncertainty-geometric defence improves clean accuracy by up to 43% and adversarial robustness by up to 65% on NLU and security benchmarks.
citing papers explorer
-
PhantomBench: Benchmarking the Non-existential Threat of Language Models
PhantomBench is a new benchmark of 60K+ non-existent terms showing language models hallucinate at rates up to 86.7 percent even when inputs assume the concepts exist.
-
Learning When to Translate for Multilingual Reasoning
Luar is a reinforcement learning method enabling reasoning language models to decide when to invoke English translation for improved multilingual reasoning.
-
Task Abstention for Large Language Models in Code Generation
A distribution-free abstention rule grounded in multiple hypothesis testing uses execution consistency to let code LLMs avoid hallucination-prone tasks with theoretical guarantees.
-
KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
KARL uses a knowledge-boundary-aware reward from within-group response statistics and two-stage RL training to align LLM abstention with actual knowledge, yielding a better accuracy-hallucination trade-off on benchmarks.
-
LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations
LoVeC uses RL to train LLMs to output verbalized numerical confidence scores for statements in long-form text, achieving better calibration than self-consistency baselines on QA datasets while being 20x faster.
-
When AI Says It Feels
LLMs trained via rubric-based self-rewarding RL with GRPO enhanced feeling expression and sycophancy robustness but degraded truthful QA performance.
-
Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality
Exploration-Commitment Decoupling instantiated as Calibration-Aware Generation improves long-form factuality by up to 13% and reduces decoding time by up to 37% on five benchmarks.
-
Hybrid Adversarial Defence for Natural Language Understanding Tasks
Hybrid entropy-uncertainty-geometric defence improves clean accuracy by up to 43% and adversarial robustness by up to 65% on NLU and security benchmarks.