Search Results for author:
Found 12 papers, 1 papers with code
SeMe: Training-Free Language Model Merging via Semantic Alignment
Despite the remarkable capabilities of Language Models (LMs) across diverse tasks, no single model consistently outperforms others, necessitating efficient methods to combine their strengths without expensive retraining.
A Semantic-based Optimization Approach for Repairing LLMs: Case Study on Code Generation
Language Models (LMs) are widely used in software engineering for code generation, but they may produce code with errors.
MORTAR: Metamorphic Multi-turn Testing for LLM-based Dialogue Systems
In this paper, we propose MORTAR, a MetamORphic multi-TuRn diAlogue testing appRoach, which mitigates the test oracle problem in the assessment of LLM-based dialogue systems.
Automated Trustworthiness Oracle Generation for Machine Learning Text Classifiers
We compare TOKI with a naive baseline based solely on model confidence and TOKI-guided adversarial attack method with A2T, a SOTA adversarial attack method.
A Semantic-based Layer Freezing Approach to Efficient Fine-Tuning of Language Models
Existing work, such as parameter-efficient finetuning (PEFT), often focuses on \textit{how to finetune} but neglects the issue of \textit{where to finetune}.
Vocabulary-Defined Semantics: Latent Space Clustering for Improving In-Context Learning
To address this, we propose complementing in-context learning with an additional clustering operation.
Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation
MINT leverages the semantic property of language models to perform neuron-level repairs in a novel way.
E-APR: Mapping the Effectiveness of Automated Program Repair
We introduce a new approach, Explaining Automated Program Repair (E-APR), which identifies features of buggy programs that explain why a particular instance is difficult for an APR technique.
Software Engineering
The Neighbours' Similar Fitness Property for Local Search
For most practical optimisation problems local search outperforms random sampling - despite the "No Free Lunch Theorem".
Is perturbation an effective restart strategy?
Premature convergence can be detrimental to the performance of search methods, which is why many search algorithms include restart strategies to deal with it.
Swarm Behaviour Evolution via Rule Sharing and Novelty Search
We present in this paper an exertion of our previous work by increasing the robustness and coverage of the evolution search via hybridisation with a state-of-the-art novelty search and accelerate the individual agent behaviour searches via a novel behaviour-component sharing technique.
Robotic Hierarchical Graph Neurons. A novel implementation of HGN for swarm robotic behaviour control
This new HGN is called Robotic-HGN (R-HGN), as it matches robot environment observations to environment labels via fusion of match probabilities from both temporal and intra-swarm collections.
