English
Related papers

Related papers: SynthSAEBench: Evaluating Sparse Autoencoders on S…

200 papers

Large Language Model (LLM) deployment requires guiding the LLM to recognize and not answer unsafe prompts while complying with safe prompts. Previous methods for achieving this require adjusting model weights along with other expensive…

Machine Learning · Computer Science 2025-11-04 Samaksh Bhargav , Zining Zhu

Large Language Models (LLMs) are predominantly evaluated on Standard American English (SAE), often overlooking the diversity of global English varieties. This narrow focus may raise fairness concerns as degraded performance on non-standard…

Computation and Language · Computer Science 2025-10-10 Jiyoung Lee , Seungho Kim , Jieun Han , Jun-Min Lee , Kitaek Kim , Alice Oh , Edward Choi

Artificial Text Detection (ATD) is becoming increasingly important with the rise of advanced Large Language Models (LLMs). Despite numerous efforts, no single algorithm performs consistently well across different types of unseen text or…

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability research for large language models; however, the state-of-the-art method of using $k$-sparse autoencoders lacks a theoretical grounding for selecting the…

Machine Learning · Computer Science 2025-08-11 Sewoong Lee , Adam Davies , Marc E. Canby , Julia Hockenmaier

Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. However, training reliable RMs under limited resources remains…

Artificial Intelligence · Computer Science 2025-11-12 Dengcan Liu , Jiahao Li , Zheren Fu , Yi Tu , Jiajun Li , Zhendong Mao , Yongdong Zhang

Understanding how features evolve across layers in deep neural networks is a fundamental challenge in mechanistic interpretability, particularly due to polysemanticity and feature superposition. While Sparse Autoencoders (SAEs) have been…

Machine Learning · Computer Science 2025-03-04 Nikita Balagansky , Ian Maksimov , Daniil Gavrilov

The rapid advancement of Large Language Models (LLMs) in software engineering has revealed critical limitations in existing benchmarks, particularly the widely used SWE-bench dataset. Recent studies have uncovered severe data contamination…

Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming to extract and analyze biologically meaningful features from…

Quantitative Methods · Quantitative Biology 2026-01-21 Xiangyu Liu , Haodi Lei , Yi Liu , Yang Liu , Wei Hu

Large language models (LLMs) have demonstrated significant advancements in reasoning and code generation, but efficiently creating new benchmarks to evaluate these capabilities remains a challenge. Traditional benchmark creation relies on…

Computation and Language · Computer Science 2026-05-27 Ishir Garg , Neel Kolhe , Xuandong Zhao , Dawn Song

Sparse Autoencoders have emerged as powerful tools for interpreting the internal representations of Large Language Models, yet they often fail to capture domain-specific features not prevalent in their training corpora. This paper…

Machine Learning · Computer Science 2025-07-18 Nikita Koriagin , Yaroslav Aksenov , Daniil Laptev , Gleb Gerasimov , Nikita Balagansky , Daniil Gavrilov

Autonomous agents are increasingly expected to support scientific research, and recent benchmarks report progress in code repair and autonomous experimentation. However, these evaluations typically assume a pre-configured execution…

Software Engineering · Computer Science 2026-03-12 Yubang Wang , Chenxi Zhang , Bowen Chen , Zezheng Huai , Zihao Dai , Xinchi Chen , Yuxin Wang , Yining Zheng , Jingjing Gong , Xipeng Qiu

Error correction is an important capability when applying large language models (LLMs) to facilitate user typing on mobile devices. In this paper, we use LLMs to synthesize a high-quality dataset of error correction pairs to evaluate and…

Machine Learning · Computer Science 2025-05-27 Yanxiang Zhang , Zheng Xu , Shanshan Wu , Yuanbo Zhang , Daniel Ramage

This report investigates enhancing semantic caching effectiveness by employing specialized, fine-tuned embedding models. Semantic caching relies on embedding similarity rather than exact key matching, presenting unique challenges in…

Effective document reranking is essential for improving search relevance across diverse applications. While Large Language Models (LLMs) excel at reranking due to their deep semantic understanding and reasoning, their high computational…

Computation and Language · Computer Science 2025-10-03 Dimitar Peshevski , Kiril Blazhevski , Martin Popovski , Gjorgji Madjarov

Audio pretrained models are widely employed to solve various tasks in speech processing, sound event detection, or music information retrieval. However, the representations learned by these models are unclear, and their analysis mainly…

No existing dataset adequately tests how well language models can incrementally update entity summaries - a crucial ability as these models rapidly advance. The Incremental Entity Summarization (IES) task is vital for maintaining accurate,…

Computation and Language · Computer Science 2024-06-10 Eunjeong Hwang , Yichao Zhou , Beliz Gunel , James Bradley Wendt , Sandeep Tata

For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and…

Determining company similarity is a vital task in finance, underpinning risk management, hedging, and portfolio diversification. Practitioners often rely on sector and industry classifications such as SIC and GICS codes to gauge similarity,…

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Zhenyu Lu , Liupeng Li , Jinpeng Wang , Haoqian Kang , Yan Feng , Ke Chen , Yaowei Wang

Sparse Autoencoders (SAEs) are widely used to interpret neural networks by identifying meaningful concepts from their representations. However, do SAEs truly uncover all concepts a model relies on, or are they inherently biased toward…

Machine Learning · Computer Science 2025-12-03 Sai Sumedh R. Hindupur , Ekdeep Singh Lubana , Thomas Fel , Demba Ba