activity
20242026
most citedDetoxBench: Benchmarking Large Language Models for Multitask Fraud & Abuse Detection

1 citations · 1 across the 9 of their papers we have counts for

collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2026

TeamLLM: A Human-Like Team-Oriented Collaboration Framework for Multi-Step Contextualized Tasks

Xiangyu Wang, Jin Wu, Haoran Shi +3

Recently, multi-Large Language Model (LLM) frameworks have been proposed to solve contextualized tasks. However, these frameworks do not explicitly emulate human team role division…

cs.CL2026

Asymmetric Actor-Critic for Multi-turn LLM Agents

Shuli Jiang, Zhaoyang Zhang, Yi Zhang +3

Large language models (LLMs) exhibit strong reasoning and conversational abilities, but ensuring reliable behavior in multi-turn interactions remains challenging. In many real-worl…

cs.CL2025

Ideology as a Problem: Lightweight Logit Steering for Annotator-Specific Alignment in Social Media Analysis

Wei Xia, Haowen Tang, Luozheng Li

LLMs internally organize political ideology along low-dimensional structures that are partially, but not fully aligned with human ideological space. This misalignment is systematic…

cs.CL2025

SDA: Steering-Driven Distribution Alignment for Open LLMs without Fine-Tuning

Wei Xia, Zhi-Hong Deng

With the rapid advancement of large language models (LLMs), their deployment in real-world applications has become increasingly widespread. LLMs are expected to deliver robust perf…

cs.CL2025

Learning to Focus: Focal Attention for Selective and Scalable Transformers

Dhananjay Ram, Wei Xia, Stefano Soatto

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces nois…

cs.CL2025

Maximally-Informative Retrieval for State Space Model Generation

Evan Becker, Benjamin Bowman, Matthew Trager +4

Given a query and dataset, the optimal way of answering the query is to make use all the information available. Modern LLMs exhibit impressive ability to memorize training data, bu…