English
Related papers

Related papers: Distributed Interpretability and Control for Large…

200 papers

Large language models (LLMs) are increasingly used in everyday tools and applications, raising concerns about their potential influence on political views. While prior research has shown that LLMs often exhibit measurable political…

Computation and Language · Computer Science 2025-11-03 Daniil Gurgurov , Katharina Trinley , Ivan Vykopal , Josef van Genabith , Simon Ostermann , Roberto Zamparelli

Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering…

Computation and Language · Computer Science 2026-03-13 Mehdi Jafari , Hao Xue , Flora Salim

Large vision-language models (LVLMs) have demonstrated exceptional capabilities in understanding visual information with human languages but also exhibit an imbalance in multilingual capabilities. In this work, we delve into the…

Computation and Language · Computer Science 2025-08-27 Yuchun Fan , Yilin Wang , Yongyu Mu , Lei Huang , Bei Li , Xiaocheng Feng , Tong Xiao , Jingbo Zhu

Small language models (SLMs) in the 100M-10B parameter range increasingly power production systems, yet whether they possess the internal emotion representations recently discovered in frontier models remains unknown. We present the first…

Computation and Language · Computer Science 2026-04-07 Jihoon Jeong

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…

Cryptography and Security · Computer Science 2026-05-21 Junxi Chen , Junhao Dong , Xiaohua Xie

Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows linearly, limiting long-context processing. Building large…

Large Language Models (LLMs) have shown impressive versatility as general purpose models. However, their broad applicability comes at a high-cost computational overhead, particularly in auto-regressive decoding where each step requires a…

Computation and Language · Computer Science 2025-08-04 Itay Nakash , Nitay Calderon , Eyal Ben David , Elad Hoffer , Roi Reichart

Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical…

Multimodal Large Language Models (LLMs) claim "musical understanding" via evaluations that conflate listening with score reading. We benchmark three SOTA LLMs (Gemini 2.5 Pro, Gemini 2.5 Flash, and Qwen2.5-Omni) across three core music…

Sound · Computer Science 2025-10-28 Brandon James Carone , Iran R. Roman , Pablo Ripollés

Recent work in activation steering has demonstrated the potential to better control the outputs of Large Language Models (LLMs), but it involves finding steering vectors. This is difficult because engineers do not typically know how…

Computation and Language · Computer Science 2023-12-08 Ole Jorgensen , Dylan Cope , Nandi Schoots , Murray Shanahan

Large Language Models (LLMs) typically have billions of parameters and are thus often difficult to interpret in their operation. In this work, we demonstrate that it is possible to decode neuron weights directly into token probabilities…

Computation and Language · Computer Science 2025-03-03 Harry J Davies

Evaluating Large Language Models (LLMs) in open-ended scenarios is challenging because existing benchmarks and metrics can not measure them comprehensively. To address this problem, we propose to fine-tune LLMs as scalable judges (JudgeLM)…

Computation and Language · Computer Science 2025-03-04 Lianghui Zhu , Xinggang Wang , Xinlong Wang

Large Multimodal Model (LMM) is a hot research topic in the computer vision area and has also demonstrated remarkable potential across multiple disciplinary fields. A recent trend is to further extend and enhance the perception capabilities…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Yang Jiao , Shaoxiang Chen , Zequn Jie , Jingjing Chen , Lin Ma , Yu-Gang Jiang

This study investigates the adoption of open-access, locally deployable causal large language models (LLMs) for travel mode choice prediction and introduces LiTransMC, the first fine-tuned causal LLM developed for this task. We…

Computation and Language · Computer Science 2025-10-08 Tareq Alsaleh , Bilal Farooq

Recent advances in legged locomotion learning are still dominated by the utilization of geometric representations of the environment, limiting the robot's capability to respond to higher-level semantics such as human instructions. To…

Robotics · Computer Science 2026-02-12 I Made Aswin Nahrendra , Seunghyun Lee , Dongkyu Lee , Hyun Myung

Large language models (LLMs) have been shown to be capable of impressive few-shot generalisation to new tasks. However, they still tend to perform poorly on multi-step logical reasoning problems. Here we carry out a comprehensive evaluation…

Artificial Intelligence · Computer Science 2022-05-20 Antonia Creswell , Murray Shanahan , Irina Higgins

Recently developed large language models (LLMs) such as ChatGPT, Claude, and Llama have demonstrated impressive abilities, and even surpass human-level performance in several tasks. Despite their success, the resource-intensive demands of…

Computation and Language · Computer Science 2024-06-17 Jie Wu , Yufeng Zhu , Lei Shen , Xuqing Lu

Large Multi-Modal Models (LMMs) have demonstrated impressive capabilities as general-purpose chatbots able to engage in conversations about visual inputs. However, their responses are influenced by societal biases present in their training…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Neale Ratzlaff , Matthew Lyle Olson , Musashi Hinck , Estelle Aflalo , Shao-Yen Tseng , Vasudev Lal , Phillip Howard

We present a novel approach to bias mitigation in large language models (LLMs) by applying steering vectors to modify model activations in forward passes. We compute 8 steering vectors, each corresponding to a different social bias axis,…

Machine Learning · Computer Science 2026-03-31 Zara Siddique , Irtaza Khalid , Liam D. Turner , Luis Espinosa-Anke

We present a practical system for privacy-aware large language model (LLM) inference that splits a transformer between a trusted local GPU and an untrusted cloud GPU, communicating only intermediate activations over the network. Our system…

Cryptography and Security · Computer Science 2026-02-20 Michael Cunningham