When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMs

Model merging has become the default way to give an aligned language model new skills without retraining: a practitioner folds task vectors from math, code, or domain specialists into a safety-aligned base using task arithmetic, TIES, or DARE. This convenience is known to carry a safety cost, but almost all of that evidence rests on static refusal tests: fixed harmful prompts scored for compliance. We argue this is misleading. Because safety alignment is "shallow," concentrated in the first few generated tokens, a merged model's static refusal can stay clean while a real adaptive attack still breaks it. We introduce SkillSafe-Bench, a controlled benchmark that scores skill-merged models on static refusal, adaptive jailbreak robustness, and capability retention under a conservative two-judge AND rule. Across six open-weight bases (five families, two scales), static safety does not predict robustness to attack: under a semantic template attack, safe-looking merges on the fragile bases (both Qwen scales and Gemma) are jailbroken 60-76% of the time while others (Llama, Phi-4) stay robust. We further show the static effect of merging is base-conditional, characterize same-recipe abliteration-style safety erosion through a data-free geometric signal (the overlap of a task vector with a safety subspace), and outline SubSafe-Merge, which projects this overlap away to remove that erosion at held capability. Adaptive evaluation is not optional for merged LLMs: the models that most need it look safe under static screening.

A Token-wise CNN-based Method for Sentence Compression

Sentence compression is a Natural Language Processing (NLP) task aimed at shortening original sentences and preserving their key information. Its applications can benefit many fields e.g. one can build tools for language education. However, current methods are largely based on Recurrent Neural Network (RNN) models which suffer from poor processing speed. To address this issue, in this paper, we propose a token-wise Convolutional Neural Network, a CNN-based model along with pre-trained Bidirectional Encoder Representations from Transformers (BERT) features for deletion-based sentence compression. We also compare our model with RNN-based models and fine-tuned BERT. Although one of the RNN-based models outperforms marginally other models given the same input, our CNN-based model was ten times faster than the RNN-based approach.

Named Entity Recognition for Novel Types by Transfer Learning

In named entity recognition, we often don't have a large in-domain training corpus or a knowledge base with adequate coverage to train a model directly. In this paper, we propose a method where, given training data in a related domain with similar (but not identical) named entity (NE) types and a small amount of in-domain training data, we use transfer learning to learn a domain-specific NE model. That is, the novelty in the task setup is that we assume not just domain mismatch, but also label mismatch.

Big Data Small Data, In Domain Out-of Domain, Known Word Unknown Word: The Impact of Word Representation on Sequence Labelling Tasks

Word embeddings -- distributed word representations that can be learned from unlabelled data -- have been shown to have high utility in many natural language processing applications. In this paper, we perform an extrinsic evaluation of five popular word embedding methods in the context of four sequence labelling tasks: POS-tagging, syntactic chunking, NER and MWE identification. A particular focus of the paper is analysing the effects of task-based updating of word representations. We show that when using word embeddings as features, as few as several hundred training instances are sufficient to achieve competitive results, and that word embeddings lead to improvements over OOV words and out of domain. Perhaps more surprisingly, our results indicate there is little difference between the different word embedding methods, and that simple Brown clusters are often competitive with word embeddings across all tasks we consider.