activity
20242026
collaborators

10 papers

cs.CL2026

Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers

Haris Riaz, Hyungji Kim, Mihai Surdeanu

Positional embeddings (PE) in Transformers encode token distance and order but are largely agnostic to \textit{syntactic structure}. We introduce \textbf{S}yntax-\textbf{i}nformed…

cs.CL2026

The Answer Lies Within: Self-Derived Rewards Enable Explainable Relation Extraction

Xinyu Guo, Zhengliang Shi, Minglai Yang +1

Despite the remarkable reasoning capabilities of large language models, they still struggle with one-shot relation extraction without predefined relation labels. We identify two pi…

cs.CY2026

Understanding Cultural Alignment in Multilingual LLMs via Natural Debate Statements

Vlad-Andrei Negru, Camelia Lemnaru, Mihai Surdeanu +1

In this work we investigate the sociocultural values learned by large language models (LLMs). We introduce a novel open-access dataset, Sociocultural Statements, constructed from n…

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

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…