works on

From the 1 of 15 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CLShow all

11 papers · 1 filter

cs.CL2026

Dual-Path LLM Reasoning for Multimodal Few-Shot Knowledge Graph Completion

Jinlan Liu, Zhiying Tu, Yongchao Xing +5

The paper introduces DuPLeR, a dual-path reasoning framework that combines large language model priors with multimodal signals to improve few-shot and zero-shot knowledge graph com…

cs.CL2026

SkillWiki: A Living Knowledge Infrastructure for Agent Skills

Dingcheng Huang, Yuda Ding, Bingshuo Liu +8

While knowledge is managed through Wikipedia and software through GitHub, agent skills still lack an infrastructure for large-scale production, governance, and evolution. SkillWiki…

cs.CL2026

Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives

Zecheng Wang, Deyuan Liu, Chunshan Li +5

Standard negative log-likelihood (NLL) for Supervised Fine-Tuning (SFT) applies uniform token-level weighting. This rigidity creates a two-fold failure mode: (i) overemphasizing lo…

cs.CL2026

Beyond Confidence: The Rhythms of Reasoning in Generative Models

Deyuan Liu, Zecheng Wang, Zhanyue Qin +3

Large Language Models (LLMs) exhibit impressive capabilities yet suffer from sensitivity to slight input context variations, hampering reliability. Conventional metrics like accura…

cs.CL2026

EchoReview: Learning Peer Review from the Echoes of Scientific Citations

Yinuo Zhang, Dingcheng Huang, Haifeng Suo +9

As the volume of scientific submissions continues to grow rapidly, traditional peer review systems are facing unprecedented scalability pressures, highlighting the urgent need for…

cs.CL2025

A Survey on Data Selection for LLM Instruction Tuning

Bolin Zhang, Jiahao Wang, Qianlong Du +3

Instruction tuning is a vital step of training large language models (LLMs), so how to enhance the effect of instruction tuning has received increased attention. Existing works ind…