Related papers: Rethinking LLM Evaluation: Can We Evaluate LLMs wi…

Large language models (LLMs) significantly enhance the performance of various applications, but they are computationally intensive and energy-demanding. This makes it challenging to deploy them on devices with limited resources, such as…

Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without the need for joint training or access to all task data. While…

Sustainability reports are critical for ESG assessment, yet greenwashing and vague claims often undermine their reliability. Existing NLP models lack robustness to these practices, typically relying on surface-level patterns that generalize…

Due to the substantial scale of Large Language Models (LLMs), the direct application of conventional compression methodologies proves impractical. The computational demands associated with even minimal gradient updates present challenges,…

Organizations increasingly rely on proprietary enterprise data, including HR records, structured reports, and tabular documents, for critical decision-making. While Large Language Models (LLMs) have strong generative capabilities, they are…

Search queries with superlatives (e.g., best, most popular) require comparing candidates across multiple dimensions, demanding linguistic understanding and domain knowledge. We show that LLMs can uncover latent intent behind these…

Environmental, Social, and Governance (ESG) reports are central to investment decision-making, yet their length, heterogeneous content, and lack of standardized structure make manual analysis costly and inconsistent. We present ESGLens, a…

Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and distillation, have been embraced to compress LLMs, targeting…

This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute. Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple…

The prohibitive cost of evaluating large language models (LLMs) on comprehensive benchmarks necessitates the creation of small yet representative data subsets (i.e., tiny benchmarks) that enable efficient assessment while retaining…

Field-Programmable Gate Arrays (FPGAs) are widely used in modern hardware design, yet writing Hardware Description Language (HDL) code for FPGA implementation remains a complex and time-consuming task. Large Language Models (LLMs) have…

Pretraining large language models (LLMs) on vast and heterogeneous datasets is crucial for achieving state-of-the-art performance across diverse downstream tasks. However, current training paradigms treat all samples equally, overlooking…

LLM-based recommender systems have made significant progress; however, the deployment cost associated with the large parameter volume of LLMs still hinders their real-world applications. This work explores parameter pruning to improve…

Existing approaches typically rely on large-scale fine-tuning to adapt LLMs for information reranking tasks, which is computationally expensive. In this work, we demonstrate that modern LLMs can be effectively adapted using only minimal,…

Aggregating multiple learners through an ensemble of models aim to make better predictions by capturing the underlying distribution of the data more accurately. Different ensembling methods, such as bagging, boosting, and stacking/blending,…

Large language models (LLMs) have demonstrated significant utility in real-world applications, exhibiting impressive capabilities in natural language processing and understanding. Benchmark evaluations are crucial for assessing the…

Optimization benchmarks play a fundamental role in assessing algorithm performance; however, existing artificial benchmarks often fail to capture the diversity and irregularity of real-world problem structures, while benchmarks derived from…

Automating the conversion of UI images into web code is a critical task for front-end development and rapid prototyping. Advances in multimodal large language models (MLLMs) have made WebUI-to-Code increasingly feasible, yet existing…

Recent progress in LLMs, such as reasoning models, has demonstrated strong abilities to solve complex competitive programming problems, often rivaling top human competitors. However, it remains underexplored whether these abilities…

Recently, Sharma et al. suggested a method called Layer-SElective-Rank reduction (LASER) which demonstrated that pruning high-order components of carefully chosen LLM's weight matrices can boost downstream accuracy -- without any…