Image de couverture de livre

When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Goren, Shani, Galil, Ido, El-Yaniv, Ran
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Hierarchical Selective Classification
par: Goren, Shani, et autres
Publié: (2024)

Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips
par: Galil, Ido, et autres
Publié: (2025)

When More is Less: Understanding Chain-of-Thought Length in LLMs
par: Wu, Yuyang, et autres
Publié: (2025)

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage
par: Hu, Junhao, et autres
Publié: (2026)

Retrieval Augmented Question Answering: When Should LLMs Admit Ignorance?
par: Wang, Dingmin, et autres
Publié: (2025)

Selective Attention Improves Transformer
par: Leviathan, Yaniv, et autres
Publié: (2024)

Prompt Repetition Improves Non-Reasoning LLMs
par: Leviathan, Yaniv, et autres
Publié: (2025)

Should We Attend More or Less? Modulating Attention for Fairness
par: Zayed, Abdelrahman, et autres
Publié: (2023)

Linguistic Calibration of Long-Form Generations
par: Band, Neil, et autres
Publié: (2024)

Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation
par: Bhardwaj, Dhrupad, et autres
Publié: (2025)

LLMs Should Express Uncertainty Explicitly
par: Guo, Junyu, et autres
Publié: (2026)

Can AI-Generated Text be Reliably Detected?
par: Sadasivan, Vinu Sankar, et autres
Publié: (2023)

ChaI-TeA: A Benchmark for Evaluating Autocompletion of Interactions with LLM-based Chatbots
par: Goren, Shani, et autres
Publié: (2024)

RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
par: Qu, Yuxiao, et autres
Publié: (2025)

When Less is Enough: Efficient Inference via Collaborative Reasoning
par: Chen, Yilei, et autres
Publié: (2026)

Multiple Abstraction Level Retrieve Augment Generation
par: Zheng, Zheng, et autres
Publié: (2025)

Real-Time Detection of Hallucinated Entities in Long-Form Generation
par: Obeso, Oscar, et autres
Publié: (2025)

Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality
par: Li, Junliang, et autres
Publié: (2025)

When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
par: Xu, Haoming, et autres
Publié: (2026)

Toxicity Detection Should Measure Contextual Harm, Not Text-Intrinsic Badness
par: Berezin, Sergei, et autres
Publié: (2025)

IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation
par: Fan, Haozhi, et autres
Publié: (2026)

Less is More: Improving LLM Alignment via Preference Data Selection
par: Deng, Xun, et autres
Publié: (2025)

LongRecall: A Structured Approach for Robust Recall Evaluation in Long-Form Text
par: Ardestani, MohamamdJavad, et autres
Publié: (2025)

Reflection-Window Decoding: Text Generation with Selective Refinement
par: Tang, Zeyu, et autres
Publié: (2025)

Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems
par: Khan, Zaid, et autres
Publié: (2025)

Exploring the Hidden Capacity of LLMs for One-Step Text Generation
par: Mezentsev, Gleb, et autres
Publié: (2025)

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
par: Wu, Yuhao, et autres
Publié: (2025)

LoRA Learns Less and Forgets Less
par: Biderman, Dan, et autres
Publié: (2024)

Multi-group Uncertainty Quantification for Long-form Text Generation
par: Liu, Terrance, et autres
Publié: (2024)

Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs
par: Zhang, Yifei, et autres
Publié: (2024)

Unraveling Text Generation in LLMs: A Stochastic Differential Equation Approach
par: Zhang, Yukun
Publié: (2024)

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
par: Hans, Abhimanyu, et autres
Publié: (2024)

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
par: Wu, Wei, et autres
Publié: (2024)

Focus On This, Not That! Steering LLMs with Adaptive Feature Specification
par: Lamb, Tom A., et autres
Publié: (2024)

Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM
par: Liu, Yibai, et autres
Publié: (2025)

Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky
par: Hathidara, Ashutosh, et autres
Publié: (2025)

ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
par: You, Haoran, et autres
Publié: (2024)

Capturing Sparks of Abstraction for the ARC Challenge
par: Andrews, Martin
Publié: (2024)

When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Generation
par: Faisal, Faizan
Publié: (2026)

LongForm: Effective Instruction Tuning with Reverse Instructions
par: Köksal, Abdullatif, et autres
Publié: (2023)