English
Related papers

Related papers: Steering Language Models with Weight Arithmetic

200 papers

Finetuning large language models on narrowly harmful datasets can cause them to become emergently misaligned, giving stereotypically `evil' responses across diverse unrelated settings. Concerningly, a pre-registered survey of experts failed…

Artificial Intelligence · Computer Science 2026-02-10 Anna Soligo , Edward Turner , Senthooran Rajamanoharan , Neel Nanda

Language model post-training has enhanced instruction-following and performance on many downstream tasks, but also comes with an often-overlooked cost on tasks with many possible valid answers. On many tasks such as creative writing,…

Computation and Language · Computer Science 2026-03-04 Taylor Sorensen , Benjamin Newman , Jared Moore , Chan Park , Jillian Fisher , Niloofar Mireshghallah , Liwei Jiang , Yejin Choi

Stereotypical bias encoded in language models (LMs) poses a threat to safe language technology, yet our understanding of how bias manifests in the parameters of LMs remains incomplete. We introduce local contrastive editing that enables the…

Computation and Language · Computer Science 2025-08-05 Marlene Lutz , Rochelle Choenni , Markus Strohmaier , Anne Lauscher

Large Language Models (LLMs) are known for their expensive and time-consuming training. Thus, oftentimes, LLMs are fine-tuned to address a specific task, given the pretrained weights of a pre-trained LLM considered a foundation model. In…

Computation and Language · Computer Science 2025-12-05 Eshed Gal , Moshe Eliasof , Javier Turek , Uri Ascher , Eran Treister , Eldad Haber

Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing methods attempt to restore safety by incorporating…

Computation and Language · Computer Science 2025-08-29 Hua Farn , Hsuan Su , Shachi H Kumar , Saurav Sahay , Shang-Tse Chen , Hung-yi Lee

While the real world is inherently stochastic, Large Language Models (LLMs) are predominantly evaluated on single-round inference against fixed ground truths. In this work, we shift the lens to distribution alignment: assessing whether…

Computation and Language · Computer Science 2026-04-08 Yanbei Jiang , Amr Keleg , Ryandito Diandaru , Jey Han Lau , Lea Frermann , Biaoyan Fang , Fajri Koto

Large language models (LLMs) are a promising avenue for machine translation (MT). However, current LLM-based MT systems are brittle: their effectiveness highly depends on the choice of few-shot examples and they often require extra…

This study investigates the effectiveness of reinforcement learning (RL) fine-tuning techniques on a compact language model (Qwen2.5-0.5B Base) for two challenging tasks: instruction following and mathematical reasoning. We compare…

Computation and Language · Computer Science 2025-07-29 Yifu Han , Geo Zhang

Despite the success of Instruction Tuning (IT) in training large language models (LLMs), such models often leverage spurious or biased features learnt from their training data and can become misaligned, leading to undesired behaviours.…

Machine Learning · Computer Science 2025-06-06 Tom A. Lamb , Adam Davies , Alasdair Paren , Philip H. S. Torr , Francesco Pinto

Multi-task learning (MTL) trains deep neural networks to optimize several objectives simultaneously using a shared backbone, which leads to reduced computational costs, improved data efficiency, and enhanced performance through cross-task…

Machine Learning · Computer Science 2025-09-30 Hoang Phan , Lam Tran , Quyen Tran , Ngoc N. Tran , Tuan Truong , Qi Lei , Nhat Ho , Dinh Phung , Trung Le

Large language models (LLMs) are currently aligned using techniques such as reinforcement learning from human feedback (RLHF). However, these methods use scalar rewards that can only reflect user preferences on average. Pluralistic…

Computation and Language · Computer Science 2025-08-13 Jadie Adams , Brian Hu , Emily Veenhuis , David Joy , Bharadwaj Ravichandran , Aaron Bray , Anthony Hoogs , Arslan Basharat

Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potential risk of…

Machine Learning · Computer Science 2026-03-10 Minjae Kang , Jaehyung Kim

Steering methods for language models (LMs) seek to provide fine-grained and interpretable control over model generations by variously changing model inputs, weights, or representations to adjust behavior. Recent work has shown that…

Computation and Language · Computer Science 2025-05-28 Zhengxuan Wu , Qinan Yu , Aryaman Arora , Christopher D. Manning , Christopher Potts

The outcome of Large Language Model (LLM) pre-training strongly depends on weight initialization and variance control strategies. Although the importance of initial variance control has been well documented in neural networks in general,…

Machine Learning · Computer Science 2025-03-25 Louis Owen , Abhay Kumar , Nilabhra Roy Chowdhury , Fabian Güra

Language models (LMs) are typically post-trained for desired capabilities and behaviors via weight-based or prompt-based steering, but the former is time-consuming and expensive, and the latter is not precisely controllable and often…

Computation and Language · Computer Science 2026-05-18 Sasha Cui , Zhongren Chen

Large language models have demonstrated capabilities in text generation, while their increasing parameter scales present challenges in computational and memory efficiency. Post-training sparsity (PTS), which reduces model cost by removing…

Computation and Language · Computer Science 2026-02-26 Minhao Jiang , Zhikai Li , Xuewen Liu , Jing Zhang , Mengjuan Chen , Qingyi Gu

Latent space steering methods provide a practical approach to controlling large language models by applying steering vectors to intermediate activations, guiding outputs toward desired behaviors while avoiding retraining. Despite their…

Machine Learning · Computer Science 2026-01-13 Shawn Im , Sharon Li

Large Language Models (LLMs) exhibit significant safety disparities across languages, with low-resource languages (LRLs) often bypassing safety guardrails established for high-resource languages (HRLs) like English. Existing solutions, such…

Machine Learning · Computer Science 2026-02-27 Jiaming Liang , Zhaoxin Wang , Handing Wang

Real-world large-scale datasets usually contain noisy labels and are imbalanced. Therefore, we propose derivative manipulation (DM), a novel and general example weighting approach for training robust deep models under these adverse…

Machine Learning · Computer Science 2020-10-06 Xinshao Wang , Elyor Kodirov , Yang Hua , Neil M. Robertson

Synthetic data augmentation via large language models (LLMs) allows researchers to leverage additional training data, thus enhancing the performance of downstream tasks, especially when real-world data is scarce. However, the generated data…

Machine Learning · Computer Science 2025-03-25 Hsun-Yu Kuo , Yin-Hsiang Liao , Yu-Chieh Chao , Wei-Yun Ma , Pu-Jen Cheng