← Back to all news
arXiv AI By Jian Gao, Xiao Zhang, Xun Zhu, Miao Li, Ji Wu

Task-Level Natural Language Priors as Learning Signals for Low-Resource LLM Training

Read the original on arXiv AI →

Task-Level Natural Language Priors as Learning Signals for Low-Resource LLM Training proposes Prior-Guided Tuning (PGT), a training approach that treats natural-language priors as auxiliary learning signals rather than just input context. The method introduces Contrastive Prior Steering (CPS), which adds positive and negative prior-conditioned auxiliary losses while preserving the original supervised objective. Experiments on AmbiMath, Jigsaw, and MNLI/HANS demonstrate that CPS consistently outperforms plain and prompt fine-tuning, achieving high accuracy and significant gains with limited training data.

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 AI.

Related stories

arXiv AI
Oct 12

What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training

The paper introduces CIG‑SFT, a supervised fine‑tuning method that uses conditional information gain to evaluate how much each demonstrated token reduces uncertainty about the task. By comparing token likelihoods from a frozen reference model with and without task input, the method derives a KL‑regularized projection of the current policy, yielding a scalar‑weighted SFT objective whose gradients match the projected target. Experiments on mathematical reasoning and code‑generation benchmarks show that CIG‑SFT outperforms standard SFT and adaptive fine‑tuning baselines, especially in generalizing to challenging evaluation distributions, without requiring extra data or online rollouts.

By Yuxuan Gu, Kequan Niu, Xiaocheng Feng, Yun Li, Yiqiao Yang, Bing Qin
llmsfine-tuningbenchmarks
More like this →
arXiv AI
Oct 9

SFT-as-Context Mitigates Forgetting in Supervised Fine-Tuning

The paper introduces SFT-as-context, a training‑free method that lets a parent large language model (LLM) use the response of a supervised fine‑tuned (SFT) model as context to answer queries. This approach preserves the parent model’s general capabilities while acquiring the SFT model’s specialized skills, achieving performance close to the SFT model on fine‑tuned benchmarks and near the parent model on general tasks. Experiments across 19 parent‑SFT pairs and 11 benchmarks show minimal gaps in performance, and the method can solve problems requiring both specialized and general knowledge, even when neither model alone succeeds.

By Kenan Tang, Andong Hua, Chengxuan Qian, Saket Tiwari, Yao Qin
llmsfine-tuningbenchmarks
More like this →
arXiv Machine Learning
Jun 2

When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval

arXiv:2606. 01304v1 Announce Type: new Abstract: Hard negative mining has become the dominant strategy for training retrievers, yet it faces intrinsic limitations: negatives are bounded by corpus availability, selected by retriever score rather than diagnostic value, and increasingly contaminated by false positives as the retriever improves.

By Zhicheng Zhang, Jiwei Tang, Kuicai Dong, Xiaopeng Li, Jieming Zhu, Jingyu Li, Qianhui Zhu, Fengyuan Lu, Wang Jiaheng, Gang Wang, Hai-Tao Zheng, Zhaocheng Du
llms
More like this →