Papers with vector arithmetic
Extracting Latent Steering Vectors from Pretrained Language Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. |
| Approach: | They propose to extract latent vectors directly from pretrained language model decoders without fine-tuning. |
| Outcome: | The proposed approach generates a target sentence nearly perfectly for English sentences . it outperforms pooled hidden states of models on a textual similarity benchmark . |
Towards Understanding Linear Word Analogies (P19-1)
Copied to clipboard
| Challenge: | Existing theories of word embeddings make strong assumptions about the embeddable space or word distribution. |
| Approach: | They propose a formal explanation of word analogies by adding arithmetic operators to non-linear embedding models such as skip-gram with negative sampling. |
| Outcome: | The proposed model downweights the more frequent word, as weighting schemes do ad hoc. |
Rotate King to get Queen: Word Relationships as Orthogonal Transformations in Embedding Space (D19-1)
Copied to clipboard
| Challenge: | Word embeddings have a notable property that word relationships can exist as linear substructures in the embeddable space. |
| Approach: | They propose an alternative way in which downstream models might learn these relationships: orthogonal and linear transformations. |
| Outcome: | The proposed model can learn such relationships as geometric translations, but there is no evidence that it is exclusively accurate. |
Representation Bending for Large Language Model Safety (2025.acl-long)
Copied to clipboard
Ashkan Yousefpour, Taeheon Kim, Ryan Sungmo Kwon, Seungbeen Lee, Wonje Jeung, Seungju Han, Alvin Wan, Harrison Ngan, Youngjae Yu, Jonghyun Choi
| Challenge: | Existing safety-enhancing techniques, such as fine-tuning with human feedback or adversarial training, are still vulnerable as they address specific threats and fail to generalize across unseen attacks. |
| Approach: | They propose a new approach that disrupts representations underlying harmful behaviors in Large Language Models by using loss-based fine-tuning. |
| Outcome: | The proposed approach outperforms existing methods such as Circuit Breaker, RMU, and NPO with 95% reduction in attack success rates across diverse jailbreak benchmarks. |