7 papers
PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy
Zheng Chen, Zhaoxin Feng, Yip Tin Po +3
Large language models (LLMs) exhibit sycophancy, a tendency to agree with user beliefs regardless of factual accuracy. This can reinforce misconceptions, but eliminating it entirel…
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…
Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors
Jianfei Ma, Zhaoxin Feng, Emmanuele Chersoni +1
Prompt compression shortens LLM input to reduce inference cost, yet existing methods score token importance through LM forward passes. It remains questionable whether such nuanced,…
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…
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…
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…
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…