11 citations · 27 across the 13 of their papers we have counts for
15 papers
Same Context, Different Agents: A Behavioral Study of Semantic Layers, Multi-Agent Orchestration and Memory Compaction in Data Agents
Zhivar Sourati, Marianne Menglin Liu, Zheng Wang +6
Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web. Data agents automate this, but their success depends on context.…
Probing RLVR training instability through the lens of objective-level hacking
Yiming Dong, Kun Fu, Haoyu Li +5
Prolonged reinforcement learning with verifiable rewards (RLVR) has been shown to drive continuous improvements in the reasoning capabilities of large language models, but the trai…
Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
Shaotian Yan, Kaiyuan Liu, Chen Shen +6
In this report, we introduce DASD-4B-Thinking, a lightweight yet highly capable, fully open-source reasoning model. It achieves SOTA performance among open-source models of compara…
Multi-refined Feature Enhanced Sentiment Analysis Using Contextual Instruction
Peter Atandoh, Jie Zou, Weikang Guo +2
Sentiment analysis using deep learning and pre-trained language models (PLMs) has gained significant traction due to their ability to capture rich contextual representations. Howev…
LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding
Zhivar Sourati, Zheng Wang, Marianne Menglin Liu +8
Question answering over visually rich documents (VRDs) requires reasoning not only over isolated content but also over documents' structural organization and cross-page dependencie…
OTTER: Open-Tagging via Text-Image Representation for Multi-modal Understanding
Jieer Ouyang, Xiaoneng Xiang, Zheng Wang +1
We introduce OTTER, a unified open-set multi-label tagging framework that harmonizes the stability of a curated, predefined category set with the adaptability of user-driven open t…
Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models
Sina J. Semnani, Jirayu Burapacheep, Arpandeep Khatua +3
Wikipedia is the largest open knowledge corpus, widely used worldwide and serving as a key resource for training large language models (LLMs) and retrieval-augmented generation (RA…
BlueLM-2.5-3B Technical Report
Baojiao Xiong, Boheng Chen, Chengzhi Wang +58
We present BlueLM-2.5-3B, a compact and unified dense Multimodal Large Language Model (MLLM) designed for efficient edge-device deployment, offering strong general-purpose and reas…
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
Zhengxuan Wu, Aryaman Arora, Atticus Geiger +5
Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability resea…
Fine-grained Alignment of Large Language Models for General Medication Recommendation without Overprescription
Zihao Zhao, Chenxiao Fan, Junlong Liu +5
Large language models (LLMs) holds significant promise in achieving general medication recommendation systems owing to their comprehensive interpretation of clinical notes and flex…
A Survey of LLM-based Agents in Medicine: How far are we from Baymax?
Wenxuan Wang, Zizhan Ma, Zheng Wang +5
Large Language Models (LLMs) are transforming healthcare through the development of LLM-based agents that can understand, reason about, and assist with medical tasks. This survey p…
An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage
Fan Bu, Zheng Wang, Siyi Wang +1
As Large Language Models (LLMs) become increasingly prevalent in tasks related to cultural heritage, such as generating descriptions of historical monuments, translating ancient te…
A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models
Zhihao Wang, Shiyu Liu, Jianheng Huang +5
Due to the continuous emergence of new data, version updates have become an indispensable requirement for Large Language Models (LLMs). The training paradigms for version updates o…
ReFT: Representation Finetuning for Language Models
Zhengxuan Wu, Aryaman Arora, Zheng Wang +4
Parameter-efficient finetuning (PEFT) methods seek to adapt large neural models via updates to a small number of weights. However, much prior interpretability work has shown that r…
pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
Zhengxuan Wu, Atticus Geiger, Aryaman Arora +5
Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability. To facilitate such resea…