Papers by Jiaping Feng

2 papers
Temporal Token Matters: Investigating and Interpreting the Consistency of Temporal Ordering in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) exhibit notable deficiencies in temporal reasoning . phrasing changes can lead LLMs to produce inconsistent outputs .
Approach: They investigate the mechanistic interpretability of temporal ordering within event temporal reasoning . they identify a sparse subset of attention heads that are causally responsible for reasoning outcomes .
Outcome: The proposed model outperforms other models in a variety of tasks and is validated by intervention-based experiments.
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference (2026.acl-long)

Copied to clipboard

Challenge: Existing work reveals only randomly permuted activations to the client, allowing adversaries to extract model weights.
Approach: They propose an attack that aligns differently shuffled activations to a common permutation and exploits them to extract model weights.
Outcome: The proposed attack can align shuffled activations to a common permutation and exploit them to extract model weights with a query cost of approximately $1.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations