works on

From the 1 of 39 linked papers with an AI index.

activity
20242026
most citedA Survey of Vibe Coding with Large Language Models

4 citations · 4 across the 14 of their papers we have counts for

collaborators
Showing cs.CLShow all

24 papers · 1 filter

cs.CL2026

LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure

Yueyang Wang, Baolong Bi, Shuo Lu +2

Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of deg…

cs.CL2026

Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation

Linfeng Gao, Qinggang Zhang, Baolong Bi +9

Retrieval-Augmented Generation (RAG) systems often fail to maintain contextual faithfulness, generating responses that conflict with the provided context or fail to fully leverage…

cs.CL2026

PRISM-: Differential Subspace Steering for Prompt Highlighting in Large Language Models

Yuyao Ge, Shenghua Liu, Yiwei Wang +6

Prompt highlighting steers a large language model to prioritize user-specified text spans during generation. A key challenge of existing Key-editing approaches is extracting steeri…

cs.CL2026

Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models

Yilong Xu, Jinhua Gao, Xiaoming Yu +4

Retrieval-Augmented Language Models boost task performance, owing to the retriever that provides external knowledge. Although crucial, the retriever primarily focuses on semantics…

cs.CL2026

ALiiCE: Evaluating Positional Fine-grained Citation Generation

Yilong Xu, Jinhua Gao, Xiaoming Yu +3

Large Language Model (LLM) can enhance its credibility and verifiability by generating text with citations. However, existing research on citation generation is predominantly limit…

cs.CL2026

Gated Differentiable Working Memory for Long-Context Language Modeling

Lingrui Mei, Shenghua Liu, Yiwei Wang +7

Long contexts challenge transformers: attention scores dilute across thousands of tokens, critical information is often lost in the middle, and models struggle to adapt to novel pa…