English
Related papers

Related papers: Does Representation Intervention Really Identify D…

200 papers

Large Language Models (LLMs) have demonstrated exceptional capabilities across various natural language processing tasks. Due to their training on internet-sourced datasets, LLMs can sometimes generate objectionable content, necessitating…

Computation and Language · Computer Science 2024-11-15 Leyang Hu , Boran Wang

Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it also creates a safety risk: harmful intent can be distributed…

Computation and Language · Computer Science 2026-05-15 Yu Fu , Haz Sameen Shahgir , Huanli Gong , Zhipeng Wei , N. Benjamin Erichson , Yue Dong

Reinforcement Learning (RL) can enable agents to learn complex tasks. However, it is difficult to interpret the knowledge and reuse it across tasks. Inductive biases can address such issues by explicitly providing generic yet useful…

Artificial Intelligence · Computer Science 2022-12-13 Thomas Schnürer , Malte Probst , Horst-Michael Gross

Safety-aligned language models refuse harmful requests through learned refusal behaviors encoded in their internal representations. Recent activation-based jailbreaking methods circumvent these safety mechanisms by applying orthogonal…

Machine Learning · Computer Science 2026-03-05 Geraldin Nanfack , Eugene Belilovsky , Elvis Dohmatob

Faithful generation in large language models (LLMs) is challenged by knowledge conflicts between parametric memory and external context. Existing contrastive decoding methods tuned specifically to handle conflict often lack adaptability and…

Computation and Language · Computer Science 2025-08-28 Anant Khandelwal , Manish Gupta , Puneet Agrawal

Large Language Models (LLMs) achieve remarkable performance through pretraining on extensive data. This enables efficient adaptation to diverse downstream tasks. However, the lack of interpretability in their underlying mechanisms limits…

Computation and Language · Computer Science 2025-06-03 Xintong Wang , Jingheng Pan , Liang Ding , Longyue Wang , Longqin Jiang , Xingshan Li , Chris Biemann

Large language models (LLMs) show potential as simulators of human behavior, offering a scalable way to study responses to interventions. However, because LLMs are trained largely on observational data, interventions in experiments with…

Computation and Language · Computer Science 2026-05-21 Victoria Lin , Taedong Yun , Maja Matarić , John Canny , Arthur Gretton , Alexander D'Amour

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based divergence attacks, often exhibit limited success and offer…

Computation and Language · Computer Science 2025-11-11 Myeongseob Ko , Nikhil Reddy Billa , Adam Nguyen , Charles Fleming , Ming Jin , Ruoxi Jia

We introduce Inference-Time Intervention (ITI), a technique designed to enhance the "truthfulness" of large language models (LLMs). ITI operates by shifting model activations during inference, following a set of directions across a limited…

Machine Learning · Computer Science 2024-06-27 Kenneth Li , Oam Patel , Fernanda Viégas , Hanspeter Pfister , Martin Wattenberg

Hallucination, posed as a pervasive challenge of multi-modal large language models (MLLMs), has significantly impeded their real-world usage that demands precise judgment. Existing methods mitigate this issue with either training with…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Qidong Huang , Xiaoyi Dong , Pan Zhang , Bin Wang , Conghui He , Jiaqi Wang , Dahua Lin , Weiming Zhang , Nenghai Yu

Recently, Large language models (LLMs) with powerful general capabilities have been increasingly integrated into various Web applications, while undergoing alignment training to ensure that the generated content aligns with user intent and…

Computation and Language · Computer Science 2023-10-17 Shuyu Jiang , Xingshu Chen , Rui Tang

The rapid adoption of large language models (LLMs) has enabled new forms of AI-assisted reasoning across scientific, technical, and organizational domains. However, prevailing modes of LLM use remain cognitively unstructured: problem…

Activation engineering is becoming increasingly popular as a means of online control of large language models (LLMs). In this work, we extend the idea of inference-time steering with vectors that represent a behavioral direction of interest…

Machine Learning · Computer Science 2024-11-26 Christopher M. Ackerman

Emotional Support Conversation (ESC) plays a critical role in mental health assistance by providing accessible psychological support in real-world applications. Large Language Models (LLMs) have shown strong empathetic abilities in ESC…

Computation and Language · Computer Science 2026-04-21 Lin Zhong , Renjin Zhu , Shujuan Ma , Jinhao Cui , Lingzhi Wang , Hao Chen , Qing Liao

Developing human understandable interpretation of large language models (LLMs) becomes increasingly critical for their deployment in essential domains. Mechanistic interpretability seeks to mitigate the issues through extracts…

Machine Learning · Computer Science 2026-01-30 Yuhang Liu , Erdun Gao , Dong Gong , Anton van den Hengel , Javen Qinfeng Shi

Reliable deployment of large language models (LLMs) requires accurate uncertainty estimation. Existing methods are predominantly answer-first, producing confidence only after generating an answer, which measure the correctness of a specific…

Computation and Language · Computer Science 2026-03-09 Changcheng Li , Jiancan Wu , Hengheng Zhang , Zhengsu Chen , Guo An , Junxiang Qiu , Xiang Wang , Qi Tian

Shaping inclusive representations that embrace diversity and ensure fair participation and reflections of values is at the core of many conversation-based models. However, many existing methods rely on surface inclusion using mention of…

Computation and Language · Computer Science 2025-11-11 Abeer Aldayel , Areej Alokaili

Large Language Model (LLM) unlearning aims to erase or suppress undesirable knowledge within the model, offering promise for controlling harmful or private information to prevent misuse. However, recent studies highlight its limited…

Computation and Language · Computer Science 2025-06-10 Xiaotian Ye , Mengqi Zhang , Shu Wu

Large Language Models (LLMs) face severe safety risks from jailbreak attacks, yet current safety testing largely relies on static datasets and lacks systematic criteria to evaluate test suite quality and adequacy. While coverage criteria…

Software Engineering · Computer Science 2026-05-13 Zeming Wei , Zhixin Zhang , Chengcan Wu , Yihao Zhang , Xiaokun Luan , Meng Sun

As Large Language Models become integral to decision-making, optimism about their power is tempered with concern over their errors. Users may over-rely on LLM advice that is confidently stated but wrong, or under-rely due to mistrust.…

Human-Computer Interaction · Computer Science 2025-10-30 Jessica Y. Bo , Sophia Wan , Ashton Anderson