Related papers: SCALPEL: Selective Capability Ablation via Low-ran…

Algorithm selection, a critical process of automated machine learning, aims to identify the most suitable algorithm for solving a specific problem prior to execution. Mainstream algorithm selection techniques heavily rely on problem…

Large language models (LLMs) increasingly exhibit human-like linguistic behaviors and internal representations that they could serve as computational simulators of language cognition. We ask whether LLMs can be systematically manipulated to…

Model interpretability is crucial for understanding and trusting the decisions made by complex machine learning models, such as those built with XGBoost. SHAP (SHapley Additive exPlanations) values have become a popular tool for…

Deep models are used for molecular property prediction, yet they are often difficult to interpret and may rely on spurious context rather than causal structure, which reduces reliability under distribution shift and harms predictive…

Despite recent success in large language model (LLM) reasoning, LLMs struggle with hierarchical multi-step reasoning tasks like generating complex programs. For these tasks, humans often start with a high-level algorithmic design and…

Skill Extraction involves identifying skills and qualifications mentioned in documents such as job postings and resumes. The task is commonly tackled by training supervised models using a sequence labeling approach with BIO tags. However,…

Continual learning in large language models (LLMs) is prone to catastrophic forgetting, where adapting to new tasks significantly degrades performance on previously learned ones. Existing methods typically rely on low-rank,…

Foundational models with billions of parameters which have been trained on large corpora of data have demonstrated non-trivial skills in a variety of domains. However, due to their monolithic structure, it is challenging and expensive to…

Understanding long-context visual information remains a fundamental challenge for vision-language models, particularly in agentic tasks such as GUI control and web navigation. While web pages and GUI environments are inherently structured…

Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of their capabilities. Evaluating open-source LLMs through leaderboards faces persistent issues like data…

This paper introduces ExKLoP, a novel framework designed to evaluate how effectively Large Language Models (LLMs) integrate expert knowledge into logical reasoning systems. This capability is especially valuable in engineering, where expert…

PSALM is a powerful extension of the Large Multi-modal Model (LMM) to address the segmentation task challenges. To overcome the limitation of the LMM being limited to textual output, PSALM incorporates a mask decoder and a well-designed…

Benchmarks for large language models (LLMs) have predominantly assessed short-horizon, localized reasoning. Existing long-horizon suites (e.g. SWE-bench) rely on manually curated issues, so expanding or tuning difficulty demands expensive…

Large language models (LLMs) are primarily designed to understand unstructured text. When directly applied to structured formats such as tabular data, they may struggle to discern inherent relationships and overlook critical patterns. While…

Long-context understanding has emerged as a critical capability for large language models (LLMs). However, evaluating this ability remains challenging. We present SCALAR, a benchmark designed to assess citation-grounded long-context…

Improving the effectiveness and efficiency of large language models (LLMs) simultaneously is a critical yet challenging research goal. In this paper, we find that low-rank pre-training, normally considered as efficient methods that will…

Large language model (LLM) agents have demonstrated remarkable potential in advancing scientific discovery. However, their capability in the fundamental yet crucial task of reproducing code from research papers, especially in the NLP…

Biomedical literature often uses complex language and inaccessible professional terminologies. That is why simplification plays an important role in improving public health literacy. Applying Natural Language Processing (NLP) models to…

Model editing aims to precisely alter the behaviors of large language models (LLMs) in relation to specific knowledge, while leaving unrelated knowledge intact. This approach has proven effective in addressing issues of hallucination and…

Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge lies in developing specific capabilities by identifying…