arXiv Computation and Language By Qixiu Li, Chenlong Bao, Xiang Zhu, Xiaoyong Li, Ruixin Cao, Shukai Chen, Zhenxiong Zhou

TIAO: Token Importance-Aware Policy Optimization for Text Summarization

Read the original on arXiv Computation and Language →

The paper introduces Token Importance-Aware Policy Optimization (TIAO), a reinforcement learning approach that improves text summarization by weighting token importance based on token dependency. TIAO reweights a trajectory’s advantage according to the overall dependencies of core tokens, addressing the limitation of previous methods that treat all tokens equally. Experiments demonstrate that a 7B foundation model enhanced with TIAO achieves performance comparable to GPT‑4 and GPT‑5‑nano on real‑world datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Hugging Face Trending Papers
Jul 20

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task. Our key intuition is that by training the model to distinguish good and bad tokens in a response, we naturally guide the model towards generating good tokens, while avoiding the pitfalls that come with directly training the model to generate off-policy tokens.

arXiv Machine Learning
Aug 27

Learning to summarize user information for personalized reinforcement learning from human feedback

The paper introduces PLUS, a framework that uses reinforcement learning to generate text-based summaries of individual users’ preferences, characteristics, and past conversations. These summaries condition a reward model, allowing it to predict personalized response preferences and improving reward accuracy by 11–77 % over the standard Bradley‑Terry model. PLUS demonstrates robust performance with new users and topics, achieves a 25 % improvement over existing personalized RLHF techniques, and enables zero‑shot personalization for state‑of‑the‑art models like GPT‑4.

By Hyunji Nam, Yanming Wan, Mickel Liu, Peter Ahnn, Jianxun Lian, Natasha Jaques