activity
20242026
most citedDiffusion Models for Molecules: A Survey of Methods and Tasks

6 citations · 6 across the 13 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2026

EviSD: Evidence-Conditioned Self-Distillation for Search-Augmented Agents

Jianan Xie, Xin Sun, Zhongqi Chen +4

Outcome-based reinforcement learning enables search-augmented language agents to learn from verifiable final answers, but its trajectory-level credit cannot distinguish the contrib…

cs.CL2026

NAG: A Unified Native Architecture for Encoder-free Text-Graph Modeling in Language Models

Haisong Gong, Zhibo Liu, Qiang Liu +2

Prevailing methods for integrating graphs into Language Models (LMs) typically rely on a segregated architecture: external Graph Neural Networks (GNNs) encode structural topology,…

cs.CL2025

Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG

Xin Sun, Jianan Xie, Zhongqi Chen +7

Large language models (LLMs) augmented with retrieval systems have significantly advanced natural language processing tasks by integrating external knowledge sources, enabling more…

cs.CL2025

Personalized Text Generation with Contrastive Activation Steering

Jinghao Zhang, Yuting Liu, Wenjie Wang +4

Personalized text generation aims to infer users' writing style preferences from their historical texts and generate outputs that faithfully reflect these stylistic characteristics…

cs.CL2025

Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models

Qiang Liu, Xinlong Chen, Yue Ding +4

Hallucination has emerged as a significant barrier to the effective application of Large Language Models (LLMs). In this work, we introduce a novel Attention-Guided SElf-Reflection…

cs.CL2024

Breaking Event Rumor Detection via Stance-Separated Multi-Agent Debate

Mingqing Zhang, Haisong Gong, Qiang Liu +2

The rapid spread of rumors on social media platforms during breaking events severely hinders the dissemination of the truth. Previous studies reveal that the lack of annotated reso…