activity
20242026
collaborators

5 papers

cs.LG2026

AlignSAE: Concept-Aligned Sparse Autoencoders

Minglai Yang, Xinyu Guo, Zhengliang Shi +4

Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidde…

cs.CL2025

How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark

Minglai Yang, Ethan Huang, Liang Zhang +3

We introduce Grade School Math with Distracting Context (GSM-DC), a synthetic benchmark to evaluate Large Language Models' (LLMs) reasoning robustness against systematically contro…

cs.CL2025

Say Less, Mean More: Leveraging Pragmatics in Retrieval-Augmented Generation

Haris Riaz, Ellen Riloff, Mihai Surdeanu

We propose a simple, unsupervised method that injects pragmatic principles in retrieval-augmented generation (RAG) frameworks such as Dense Passage Retrieval to enhance the utility…

cs.CL2025

CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality

Razvan-Gabriel Dumitru, Minglai Yang, Vikas Yadav +1

We introduce CopySpec, a simple yet effective technique to tackle the inefficiencies LLMs face when generating responses that closely resemble previous outputs or responses that ca…

cs.CL2024

Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy

Razvan-Gabriel Dumitru, Paul-Ioan Clotan, Vikas Yadav +2

This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs), enhancing the traditional methodology established b…