activity
20232026
most citedMitigating Shortcuts in Language Models with Soft Label Encoding

2 citations · 2 across the 7 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation

Haiyan Zhao, Zirui He, Guanchu Wang +3

Activation verbalization explains hidden representations in natural language, but existing methods are mostly limited to self-explanation, where each model explains only its own ac…

cs.CL2026

FinAnchor: Aligned Multi-Model Representations for Financial Prediction

Zirui He, Huopu Zhang, Yanguang Liu +2

Financial prediction from long documents involves significant challenges, as actionable signals are often sparse and obscured by noise, and the optimal LLM for generating embedding…

cs.CL2025

Rep2Text: Decoding Full Text from a Single LLM Token Representation

Haiyan Zhao, Zirui He, Yiming Tang +4

Large language models (LLMs) have achieved remarkable progress across diverse tasks, yet their internal mechanisms remain largely opaque. In this work, we investigate a fundamental…

cs.CL2025

LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories

Zirui He, Haiyan Zhao, Yingcong Li +2

Large language models (LLMs) are commonly evaluated on challenging benchmarks such as AIME and Math500, where benchmark contamination can make memorized solutions appear as genuine…

cs.CL2025

SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models

Zirui He, Mingyu Jin, Bo Shen +3

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but controlling their behavior reliably remains challenging…

cs.CL20232 cited

Mitigating Shortcuts in Language Models with Soft Label Encoding

Zirui He, Huiqi Deng, Haiyan Zhao +2

Recent research has shown that large language models rely on spurious correlations in the data for natural language understanding (NLU) tasks. In this work, we aim to answer the fo…