Language Models Can be Efficiently Steered via Minimal Embedding Layer Transformations

,

• Publication year

  2025

• Venue

  Conference on Empirical Methods in Natural Language Processing

• Publication date

  Unknown publication date

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/2025.emnlp-main.1170
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Generative Representational Instruction Tuning

  2024cited by this paper
• LoFiT: Localized Fine-tuning on LLM Representations

  2024cited by this paper
• Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks

  2024cited by this paper
• HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

  2024cited by this paper
• Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch

  2023cited by this paper
• Think before you speak: Training Language Models With Pause Tokens

  2023cited by this paper
• Efficient Streaming Language Models with Attention Sinks

  2023cited by this paper
• Universal and Transferable Adversarial Attacks on Aligned Language Models

  2023cited by this paper
• Judging LLM-as-a-judge with MT-Bench and Chatbot Arena

  2023cited by this paper
• SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot

  2023influential reference
• Hyperpolyglot LLMs: Cross-Lingual Interpretability in Token Embeddings

  2023cited by this paper
• Safe RLHF: Safe Reinforcement Learning from Human Feedback

  2023cited by this paper
• TRUE: Re-evaluating Factual Consistency Evaluation

  2022cited by this paper
• PaLM: Scaling Language Modeling with Pathways

  2022cited by this paper
• How to Dissect a Muppet: The Structure of Transformer Embedding Spaces

  2022cited by this paper
• Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

  2022cited by this paper
• Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, ACL 2022 - Tutorial Abstracts, Dublin, Ireland, May 22-27, 2022

  2022cited by this paper
• Self-Instruct: Aligning Language Models with Self-Generated Instructions

  2022cited by this paper
• XPrompt: Exploring the Extreme of Prompt Tuning

  2022cited by this paper
• Prefix-Tuning: Optimizing Continuous Prompts for Generation

  2021cited by this paper
• BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models

  2021cited by this paper
• The Power of Scale for Parameter-Efficient Prompt Tuning

  2021influential reference
• WARP: Word-level Adversarial ReProgramming

  2021cited by this paper
• Language Models are Few-Shot Learners

  2020cited by this paper
• Robustness Verification for Transformers

  2020cited by this paper
• Tuning

  2020cited by this paper
• MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices

  2020cited by this paper
• LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression

  2020cited by this paper
• Pretrained Transformers Improve Out-of-Distribution Robustness

  2020cited by this paper
• MAD-X: An Adapter-based Framework for Multi-task Cross-lingual Transfer

  2020cited by this paper
• On the Robustness of Language Encoders against Grammatical Errors

  2020cited by this paper
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

  2020cited by this paper
• Probing Pretrained Language Models for Lexical Semantics

  2020cited by this paper
• Parameter-Efficient Transfer Learning for NLP

  2019cited by this paper
• DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

  2019cited by this paper
• The CommitmentBank: Investigating projection in naturally occurring discourse

  2019cited by this paper
• How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings

  2019cited by this paper
• Revealing the Dark Secrets of BERT

  2019cited by this paper
• BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

  2019cited by this paper
• SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems

  2019influential reference
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  2019cited by this paper
• WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations

  2018cited by this paper
• Attention is All you Need

  2017cited by this paper
• Axiomatic Attribution for Deep Networks

  2017influential reference
• Findings of the 2016 Conference on Machine Translation

  2016cited by this paper
• Teaching Machines to Read and Comprehend

  2015cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Choice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning

  2011cited by this paper
• The Sixth PASCAL Recognizing Textual Entailment Challenge

  2009cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002influential reference

• No citing papers are available for this paper.