Related papers: Committed SAE-Feature Traces for Audited-Session S…

Large Language Models (LLMs) have demonstrated remarkable efficacy in text embedding, yet current adaptation methods like LoRA face significant bottlenecks in computational efficiency and cross-architecture transferability. Whenever a new…

When large AI models are deployed as cloud-based services, clients have no guarantee that responses are correct or were produced by the intended model. Rerunning inference locally is infeasible for large models, and existing cryptographic…

Mitigating explicit and implicit biases in Large Language Models (LLMs) has become a critical focus in the field of natural language processing. However, many current methodologies evaluate scenarios in isolation, without considering the…

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…

Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt caching to enhance inference performance by cooperatively sharing intermediate processing states…

Recent Searchable Symmetric Encryption (SSE) schemes enable secure searching over an encrypted database stored in a server while limiting the information leaked to the server. These schemes focus on hiding the access pattern, which refers…

Sparse autoencoders (SAEs) are a popular tool for interpreting large language model activations, but their utility in addressing open questions in interpretability remains unclear. In this work, we demonstrate their effectiveness by using…

Sparse autoencoders (SAEs) have been applied to large language models and protein language models, but not systematically to electronic health record (EHR) foundation models. We train TopK SAEs on FlatASCEND, a 14.5-million-parameter…

Symbolic regression (SR) seeks closed-form mathematical expressions that fit observed data. Neural SR methods amortize the search by training an encoder to map observations directly to expressions in a single pass, but this amortized…

Agent memory failures are silent: an LLM-based agent can produce a fluent response even when it fails to extract, retain, or retrieve the information needed across sessions. The write-manage-read loop describes the external pipeline of…

Large Language Model (LLM) agents are increasingly deployed for complex, multi-step software engineering (SWE) tasks. However, their trajectories often contain costly inefficiencies, such as redundant exploration, looping, and failure to…

Recent advances in split learning (SL) have established it as a promising framework for privacy-preserving, communication-efficient distributed learning at the network edge. However, SL's sequential update process is vulnerable to even a…

As sixth-generation (6G) networks advance, large language models (LLMs) are increasingly integrated into 6G infrastructure to enhance network management and intelligence. However, traditional LLMs architecture struggle to meet the stringent…

Model merging combines multiple models into a single model with aggregated capabilities, making it a powerful tool for large language model (LLM) development. However, scaling model merging is challenging: performance depends on the choice…

Closed large language models (LLMs) such as GPT-4 have set state-of-the-art results across a number of NLP tasks and have become central to NLP and machine learning (ML)-driven solutions. Closed LLMs' performance and wide adoption has…

Software vulnerabilities are now reported at an unprecedented speed due to the recent development of automated vulnerability hunting tools. However, fixing vulnerabilities still mainly depends on programmers' manual efforts. Developers need…

Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose traces or generate follow-up feedback, but they do not…

Every call to an LLM classification endpoint produces a labeled input-output pair already retained in production logs. These pairs constitute a free, growing training set: a lightweight surrogate trained on them can absorb a significant…

The emergence of spontaneous symmetry breaking among a few heads of multi-head attention (MHA) across transformer blocks in classification tasks was recently demonstrated through the quantification of single-nodal performance (SNP). This…

Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment. Prior work shows that translating malicious prompts into other languages can…