Cover Image

BOW: Reinforcement Learning for Bottlenecked Next Word Prediction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Ming, Xu, Zhikun, Dineen, Jacob, Ye, Xiao, Zhou, Ben
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

ToW: Thoughts of Words Improve Reasoning in Large Language Models
by: Xu, Zhikun, et al.
Published: (2024)

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
by: Dineen, Jacob, et al.
Published: (2026)

CC-LEARN: Cohort-based Consistency Learning
by: Ye, Xiao, et al.
Published: (2025)

QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA
by: Dineen, Jacob, et al.
Published: (2025)

On Support Samples of Next Word Prediction
by: Li, Yuqian, et al.
Published: (2025)

Evaluating Medical LLMs by Levels of Autonomy: A Survey Moving from Benchmarks to Applications
by: Ye, Xiao, et al.
Published: (2025)

Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment
by: Merrill, William, et al.
Published: (2024)

Reliable Use of Lemmas via Eligibility Reasoning and Section$-$Aware Reinforcement Learning
by: Xu, Zhikun, et al.
Published: (2026)

Unbiased Visual Reasoning with Controlled Visual Inputs
by: Li, Zhaonan, et al.
Published: (2025)

RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems
by: Srinivasan, Adarsh, et al.
Published: (2025)

Expression Syntax Information Bottleneck for Math Word Problems
by: Xiong, Jing, et al.
Published: (2023)

HieroLM: Egyptian Hieroglyph Recovery with Next Word Prediction Language Model
by: Cai, Xuheng, et al.
Published: (2025)

Reinforced Fast Weights with Next-Sequence Prediction
by: Hwang, Hee Seung, et al.
Published: (2026)

ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation
by: Liu, Qin, et al.
Published: (2025)

Predict the Next Word: Humans exhibit uncertainty in this task and language models _____
by: Ilia, Evgenia, et al.
Published: (2024)

Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission
by: Ye, Jiangnan, et al.
Published: (2026)

ThinkTuning: Instilling Cognitive Reflections without Distillation
by: RRV, Aswin, et al.
Published: (2025)

Policy Learning with a Language Bottleneck
by: Srivastava, Megha, et al.
Published: (2024)

From Words to Worth: Newborn Article Impact Prediction with LLM
by: Zhao, Penghai, et al.
Published: (2024)

Deepfake Word Detection by Next-token Prediction using Fine-tuned Whisper
by: Tran, Hoan My, et al.
Published: (2026)

Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models
by: Li, Zongqian, et al.
Published: (2026)

On Next-Token Prediction in LLMs: How End Goals Determine the Consistency of Decoding Algorithms
by: Trauger, Jacob, et al.
Published: (2025)

QoNext: Towards Next-generation QoE for Foundation Models
by: Guo, Yijin, et al.
Published: (2025)

Reinforcement World Model Learning for LLM-based Agents
by: Yu, Xiao, et al.
Published: (2026)

Next Word Suggestion using Graph Neural Network
by: Magar, Abisha Thapa, et al.
Published: (2025)

Label Words as Local Task Vectors in In-Context Learning
by: Zheng, Bowen, et al.
Published: (2024)

We Need Knowledge Distillation for Solving Math Word Problems
by: Shen, Zhenquan, et al.
Published: (2025)

From Graph to Word Bag: Introducing Domain Knowledge to Confusing Charge Prediction
by: Li, Ang, et al.
Published: (2024)

Visual Grounding Helps Learn Word Meanings in Low-Data Regimes
by: Zhuang, Chengxu, et al.
Published: (2023)

TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment
by: Li, Zheng, et al.
Published: (2025)

CLIF: Concept-Level Influence Functions for Transparent Bottleneck Models
by: Sun, Yike, et al.
Published: (2026)

Predicting the Target Word of Game-playing Conversations using a Low-Rank Dialect Adapter for Decoder Models
by: Srirag, Dipankar, et al.
Published: (2024)

Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering
by: Fu, Xingyu, et al.
Published: (2023)

Cross-Lingual Word Alignment for ASEAN Languages with Contrastive Learning
by: Zhang, Jingshen, et al.
Published: (2024)

Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning
by: Wang, Yinjie, et al.
Published: (2025)

Skill Reuse as Compression in Agentic RL
by: Xu, Zhikun, et al.
Published: (2026)

Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis
by: Cheng, Zhenxiao, et al.
Published: (2024)

Reasoning Bias of Next Token Prediction Training
by: Lin, Pengxiao, et al.
Published: (2025)

Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
by: Wang, Yinjie, et al.
Published: (2025)

Beyond Next Word Prediction: Developing Comprehensive Evaluation Frameworks for measuring LLM performance on real world applications
by: Agrawal, Vishakha, et al.
Published: (2025)