Cover Image

Linear Correlation in LM's Compositional Generalization and Hallucination

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Peng, Letian, An, Chenyang, Hao, Shibo, Dong, Chengyu, Shang, Jingbo
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Correlation and Navigation in the Vocabulary Key Representation Space of Language Models
by: Peng, Letian, et al.
Published: (2024)

Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification
by: Peng, Letian, et al.
Published: (2024)

Codifying Character Logic in Role-Playing
by: Peng, Letian, et al.
Published: (2025)

Incubating Text Classifiers Following User Instruction with Nothing but LLM
by: Peng, Letian, et al.
Published: (2024)

Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing
by: Peng, Letian, et al.
Published: (2024)

UltraGen: Extremely Fine-grained Controllable Generation via Attribute Reconstruction and Global Preference Optimization
by: Yun, Longfei, et al.
Published: (2025)

Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation
by: Peng, Letian, et al.
Published: (2023)

The Price of Format: Diversity Collapse in LLMs
by: Yun, Longfei, et al.
Published: (2025)

Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs
by: Zhou, Shang, et al.
Published: (2024)

Codified Foreshadowing-Payoff Text Generation
by: Yun, Longfei, et al.
Published: (2026)

Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM's Nest
by: Peng, Letian, et al.
Published: (2025)

Codified Finite-state Machines for Role-playing
by: Peng, Letian, et al.
Published: (2026)

Deriving Character Logic from Storyline as Codified Decision Trees
by: Peng, Letian, et al.
Published: (2026)

MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Tasks
by: Peng, Letian, et al.
Published: (2024)

When is the consistent prediction likely to be a correct prediction?
by: Nguyen, Alex, et al.
Published: (2024)

Next-Token Prediction Task Assumes Optimal Data Ordering for LLM Training in Proof Generation
by: An, Chenyang, et al.
Published: (2024)

BOOKMARKS: Efficient Active Storyline Memory for Role-playing
by: Peng, Letian, et al.
Published: (2026)

Answer is All You Need: Instruction-following Text Embedding via Answering the Question
by: Peng, Letian, et al.
Published: (2024)

Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection
by: Zhang, Yuwei, et al.
Published: (2025)

LP-LM: No Hallucinations in Question Answering with Logic Programming
by: Wu, Katherine, et al.
Published: (2025)

FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation
by: Zhang, Runzhe, et al.
Published: (2026)

Simulating Organized Group Behavior: New Framework, Benchmark, and Analysis
by: Zou, Xinkai, et al.
Published: (2026)

Watermarks for Language Models via Probabilistic Automata
by: Wang, Yangkun, et al.
Published: (2025)

GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval
by: Liu, Lingyuan, et al.
Published: (2025)

LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models
by: Han, Chi, et al.
Published: (2023)

Entangled Relations: Leveraging NLI and Meta-analysis to Enhance Biomedical Relation Extraction
by: Hogan, William, et al.
Published: (2024)

Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models
by: Mekala, Dheeraj, et al.
Published: (2024)

FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs
by: Alnuhait, Deema, et al.
Published: (2024)

BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion
by: Zhuang, Shaobin, et al.
Published: (2026)

Language Models Hallucinate, but May Excel at Fact Verification
by: Guan, Jian, et al.
Published: (2023)

Relational Linearity is a Predictor of Hallucinations
by: Lu, Yuetian, et al.
Published: (2026)

Relational Probing: LM-to-Graph Adaptation for Financial Prediction
by: Niu, Yingjie, et al.
Published: (2026)

Text Generation Beyond Discrete Token Sampling
by: Zhuang, Yufan, et al.
Published: (2025)

EmotionHallucer: Evaluating Emotion Hallucinations in Multimodal Large Language Models
by: Xing, Bohao, et al.
Published: (2025)

READ: Improving Relation Extraction from an ADversarial Perspective
by: Li, Dawei, et al.
Published: (2024)

CorrectionLM: Self-Corrections with SLM for Dialogue State Tracking
by: Lee, Chia-Hsuan, et al.
Published: (2024)

Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations
by: Ji, Ziwei, et al.
Published: (2025)

Order Matters: Rethinking Prompt Construction in In-Context Learning
by: Li, Warren, et al.
Published: (2025)

Attention Reveals More Than Tokens: Training-Free Long-Context Reasoning with Attention-guided Retrieval
by: Zhang, Yuwei, et al.
Published: (2025)

DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering
by: Nguyen, Alex, et al.
Published: (2024)