works on

From the 1 of 14 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2026

From Reasoning Depth to Reasoning Breadth: Evaluating Multi-Point Associative Reasoning in Large Language Models

Si'an Xie, Jiaxun Liu, Biao Yang +4

Large language models (LLMs) have made substantial progress on reasoning tasks that require increasingly long and complex inferential chains. This progress primarily reflects reaso…

cs.CL2026

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

FaithLM: Towards Faithful Explanations for Large Language Models

Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang +7

Large language models (LLMs) increasingly produce natural language explanations, yet these explanations often lack faithfulness, and they do not reliably reflect the evidence the m…

cs.CL2025

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering

Haiyan Zhao, Xuansheng Wu, Fan Yang +3

Linear concept vectors effectively steer LLMs, but existing methods suffer from noisy features in diverse datasets that undermine steering robustness. We propose Sparse Autoencoder…

cs.CL2025

Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution

Haiyan Zhao, Heng Zhao, Bo Shen +3

Probing learned concepts in large language models (LLMs) is crucial for understanding how semantic knowledge is encoded internally. Training linear classifiers on probing tasks is…

cs.CL2024

Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages

Zihao Li, Yucheng Shi, Zirui Liu +4

The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing s…