Towards Verifiable Text Generation with Evolving Memory and Self-Reflection
Despite the remarkable ability of large language models (LLMs) in language comprehension and generation, they often suffer from producing factually incorrect information, also known as hallucination. A promising solution to this issue is verifiable text generation, which prompts LLMs to generate content with citations for accuracy verification. However, verifiable text generation is non-trivial due to the focus-shifting phenomenon, the intricate reasoning needed to align the claim with correct citations, and the dilemma between the precision and breadth of retrieved documents. In this paper, we present VTG, an innovative framework for Verifiable Text Generation with evolving memory and self-reflection. VTG introduces evolving long short-term memory to retain both valuable documents and recent documents. A two-tier verifier equipped with an evidence finder is proposed to rethink and reflect on the relationship between the claim and citations. Furthermore, active retrieval and diverse query generation are utilized to enhance both the precision and breadth of the retrieved documents. We conduct extensive experiments on five datasets across three knowledge-intensive tasks and the results reveal that VTG significantly outperforms baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
HallucinationRetrievalText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SEDM: Scalable Self-Evolving Distributed Memory for Agents
Long-term multi-agent systems inevitably generate vast amounts of trajectories and historical interactions, which makes efficient memory management essential for both performance and scalability. Existing methods typical…
Fact VerificationSEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents
Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are i…
Reinforcement LearningMetis: Bridging Text and Code Memory for Self-Evolving Agents
Self-evolving agents improve over time by distilling experience from past executions and reusing it in future tasks. Existing systems represent such experience either as natural-language text injected into the agent cont…
EVE-Agent: Evidence-Verifiable Self-Evolving Agents
Self-evolving agents should not train on examples they cannot justify. Data-free self-evolving search agents offer a scalable route to systems that generate their own questions, answer them, and improve from their own fe…
VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following
Multimodal instruction-following models require training data that is accurate, diverse, verifiable, and challenging. Existing synthesis pipelines typically follow a one-pass generate-and-filter paradigm, discarding feed…
Reinforcement LearningInstruction Following