Cover Image

Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Si, Shuzheng, Zhao, Haozhe, Gao, Cheng, Bai, Yuzhuo, Wang, Zhitong, Gao, Bofei, Luo, Kangyang, Li, Wenhao, Huang, Yufei, Chen, Gang, Qi, Fanchao, Zhang, Minjia, Chang, Baobao, Sun, Maosong
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FaithLens: Detecting and Explaining Faithfulness Hallucination
by: Si, Shuzheng, et al.
Published: (2025)

A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks
by: Si, Shuzheng, et al.
Published: (2025)

Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering
by: Si, Shuzheng, et al.
Published: (2025)

InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs
by: Bai, Yuzhuo, et al.
Published: (2026)

GATEAU: Selecting Influential Samples for Long Context Alignment
by: Si, Shuzheng, et al.
Published: (2024)

From Context to Skills: Can Language Models Learn from Context Skillfully?
by: Si, Shuzheng, et al.
Published: (2026)

MEIC-DT: Memory-Efficient Incremental Clustering for Long-Text Coreference Resolution with Dual-Threshold Constraints
by: Luo, Kangyang, et al.
Published: (2025)

ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter Refinement
by: Luo, Kangyang, et al.
Published: (2025)

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion
by: Luo, Kangyang, et al.
Published: (2025)

Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance
by: Zhao, Haozhe, et al.
Published: (2024)

From Context to EDUs: Faithful and Structured Context Compression via Elementary Discourse Unit Decomposition
by: Zhou, Yiqing, et al.
Published: (2025)

RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context
by: Lei, Yu, et al.
Published: (2025)

KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
by: Gao, Cheng, et al.
Published: (2026)

UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
by: Zhao, Haozhe, et al.
Published: (2024)

Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints
by: An, Kaikai, et al.
Published: (2024)

Improving the Robustness of Distantly-Supervised Named Entity Recognition via Uncertainty-Aware Teacher Learning and Student-Student Collaborative Learning
by: Si, Shuzheng, et al.
Published: (2023)

Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-Distillation
by: Zhao, Haozhe, et al.
Published: (2024)

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
by: Zhao, Haozhe, et al.
Published: (2026)

SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition
by: Si, Shuzheng, et al.
Published: (2023)

MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
by: Zhao, Haozhe, et al.
Published: (2023)

UltraIF: Advancing Instruction Following from the Wild
by: An, Kaikai, et al.
Published: (2025)

MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models
by: Zhao, Haozhe, et al.
Published: (2025)

WGRAMMAR: Leverage Prior Knowledge to Accelerate Structured Decoding
by: Wang, Ran, et al.
Published: (2025)

Improving MLLM Training Efficiency via Stage-Aware Sparsity
by: Shi, Kean, et al.
Published: (2025)

Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think
by: Chen, Liang, et al.
Published: (2025)

An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
by: Chen, Liang, et al.
Published: (2024)

New characterization of full weight spectrum one-orbit cyclic subspace codes
by: Shi, Minjia, et al.
Published: (2025)

From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora
by: Shen, Yingli, et al.
Published: (2025)

Finite-time stabilization of discontinuous fuzzy inertial Cohen–Grossberg neural networks with mixed time-varying delays.
by: Fanchao Kong
Published: (2021)

What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs?
by: Gao, Shuzheng, et al.
Published: (2023)

Search-Based LLMs for Code Optimization
by: Gao, Shuzheng, et al.
Published: (2024)

SR-Eval: Evaluating LLMs on Code Generation under Stepwise Requirement Refinement
by: Zhan, Zexun, et al.
Published: (2025)

Unlocking Proactivity in Task-Oriented Dialogue
by: Zhang, Hongbin, et al.
Published: (2026)

SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback
by: Gao, Jingsheng, et al.
Published: (2024)

SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning
by: Gao, Shuzheng, et al.
Published: (2025)

Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales
by: Gao, Minghe, et al.
Published: (2024)

G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning
by: Chen, Liang, et al.
Published: (2025)

LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
by: Gao, Bofei, et al.
Published: (2024)

On the Faithfulness of Visual Thinking: Measurement and Enhancement
by: Liu, Zujing, et al.
Published: (2025)

Empirical Study of Code Large Language Models for Binary Security Patch Detection
by: Li, Qingyuan, et al.
Published: (2025)