PARENTing via Model-Agnostic Reinforcement Learning to Correct Pathological Behaviors in Data-to-Text Generation
In language generation models conditioned by structured data, the classical training via maximum likelihood almost always leads models to pick up on dataset divergence (i.e., hallucinations or omissions), and to incorporate them erroneously in their own generations at inference. In this work, we build ontop of previous Reinforcement Learning based approaches and show that a model-agnostic framework relying on the recently introduced PARENT metric is efficient at reducing both hallucinations and omissions. Evaluations on the widely used WikiBIO and WebNLG benchmarks demonstrate the effectiveness of this framework compared to state-of-the-art models.
Code (1)
Tasks
Data-to-Text Generationreinforcement-learningReinforcement Learning (RL)Text GenerationSimilar Papers 제목 키워드 기반
Parenting: Safe Reinforcement Learning from Human Input
Autonomous agents trained via reinforcement learning present numerous safety concerns: reward hacking, negative side effects, and unsafe exploration, among others. In the context of near-future autonomous agents, operati…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement LearningParenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning
Retrieval-Augmented Generation (RAG) offers an effective solution to the issues faced by Large Language Models (LLMs) in hallucination generation and knowledge obsolescence by incorporating externally retrieved knowledge…
HallucinationRAGRetrievalRetrieval-augmented GenerationPathFound: An Agentic Multimodal Model Activating Evidence-seeking Pathological Diagnosis
Recent pathological foundation models have substantially advanced visual representation learning and multimodal interaction. However, most models still rely on a static inference paradigm in which whole-slide images are …
Representation LearningReinforcement LearningDiscovering Pathology Rationale and Token Allocation for Efficient Multimodal Pathology Reasoning
Multimodal pathological image understanding has garnered widespread interest due to its potential to improve diagnostic accuracy and enable personalized treatment through integrated visual and textual data. However, exis…
Computational EfficiencyDiagnosticLesion DetectionQuestion Answering+1Gender Bias in LLMs: Preliminary Evidence from Shared Parenting Scenario in Czech Family Law
Access to justice remains limited for many people, leading laypersons to increasingly rely on Large Language Models (LLMs) for legal self-help. Laypeople use these tools intuitively, which may lead them to form expectati…