works on

From the 1 of 23 linked papers with an AI index.

activity
20242026
most citedPredict the Retrieval! Test time adaptation for Retrieval Augmented Generation

1 citations · 1 across the 4 of their papers we have counts for

collaborators

23 papers

cs.CL20261 cited

Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation

Xin Sun, Zhongqi Chen, Qiang Liu +5

The paper introduces TTARAG, a test-time adaptation technique that updates a language model's parameters during inference to better integrate retrieved knowledge for specialized do…

cs.LG2026

On the Vulnerability of Parameter-Level Defenses to Model Merging

Kuangpu Guo, Qingyan Zheng, Jian Liang +4

The training-free integration of expert models via model merging has exposed significant security risks, enabling free-riders to combine specialized models without authorization. R…

cs.LG2026

Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging

Kuangpu Guo, Aijing Yu, Jian Liang +4

Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, traditional basic merging methods often experience perf…

cs.CL2026

KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering

Xin Sun, Zhongqi Chen, Xing Zheng +6

Knowledge Base Question Answering (KBQA) challenges models to bridge the gap between natural language and strict knowledge graph schemas by generating executable logical forms. Whi…

cs.CL2026

The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?

Hao Yin, Guangzong Si, Zilei Wang

Contrastive decoding strategies are widely used to reduce object hallucinations in multimodal large language models (MLLMs). These methods work by constructing contrastive samples…

cs.CL2026

GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering

Xin Sun, Jianan Xie, Zhongqi Chen +6

Reinforcement learning (RL) is a natural fit for agentic knowledge base question answering (KBQA), where a model must issue executable actions, observe knowledge-base feedback, and…