works on

From the 1 of 6 linked papers with an AI index.

collaborators

6 papers

cs.CL2026

Know It, Act on It: Investigating Memory Utilization in LLM Personalization

Zhaoxin Feng, Jianfei Ma, Emmanuele Chersoni

As large language model (LLM) agents evolve into personalized companions, memory has emerged as a core capability. However, LLMs face a knowledge utilization problem: they may fail…

cs.CL2026

Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors

Jianfei Ma, Zhaoxin Feng, Emmanuele Chersoni +1

The paper explores using deterministic linguistic rules as prompt compressors to shorten inputs for large language models, eliminating the need for costly model-based token scoring…

cs.AI2026

What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic Curiosity

Haoxi Li, Qinglin Hou, Jianfei Ma +6

To navigate partially observable visual environments, recent VLM agents increasingly internalize world modeling capabilities into their policies via explicit CoT reasoning, enablin…

cs.CL2026

Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy

Zhaoxin Feng, Zheng Chen, Jianfei Ma +3

Alignment techniques often inadvertently induce sycophancy in LLMs. While prior studies studied this behaviour in direct-answer settings, the role of Chain-of-Thought (CoT) reasoni…

cs.CL2025

From BERT to LLMs: Comparing and Understanding Chinese Classifier Prediction in Language Models

Ziqi Zhang, Jianfei Ma, Emmanuele Chersoni +2

Classifiers are an important and defining feature of the Chinese language, and their correct prediction is key to numerous educational applications. Yet, whether the most popular L…

cs.CL2025

Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention

Zhaoxin Feng, Jianfei Ma, Emmanuele Chersoni +2

Autoregressive Large Language Models (LLMs) demonstrate exceptional performance in language understanding and generation. However, their application in text embedding tasks has bee…