|
- A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments However, this reliance on memory introduces a
- Linear-TimeSequenceModelingwithSelectiveStateSpaces
Abstract Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module Many subquadratic-time architectures such as linear attention, gated convolution and recurrent models, and structured state space models (SSMs) have been developed to address Transformers’ computational
- VideoChat-Flash: Hierarchical Compression for Long-Context Video. . .
Long-context video modeling is critical for multimodal large language models (MLLMs), enabling them to process movies, online video streams, and so on Despite its advances, handling long videos
- Roll the dice look before you leap: Going beyond the creative. . .
In these tasks, we study two types of creativity, one that requires combining pieces of knowledge (like in wordplay) and another that requires designing clever constructions (like puzzle-design or story-design)
- On the Planning Abilities of Large Language Models : A Critical . . .
While, as we mentioned earlier, there can be thorny “clever hans” issues about humans prompting LLMs, an automated verifier mechanically backprompting the LLM doesn’t suffer from these We tested this setup on a subset of the failed instances in the one-shot natural language prompt configuration using GPT-4, given its larger context window
- Ignore Previous Prompt: Attack Techniques For Language Models
Abstract Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications However, studies that explore their vulnerabilities emerging from malicious user interac-tion are scarce By proposing PROMPTINJECT, a prosaic alignment framework for mask-based iterative adversarial prompt composition, we examine how GPT
- Cross-Lingual Multi-Hop Knowledge Editing - OpenReview
Following this, we propose a significantly improved system for cross-lingual multi-hop knowledge editing, CLeVer-CKE CLeVer-CKE is based on a retrieve, verify and generate knowledge editing framework, where a retriever is formulated to recall edited facts and support an LLM to adhere to knowledge edits
- Clever: A Curated Benchmark for Formally Verified Code Generation
We introduce CLEVER, the first curated benchmark for evaluating the generation of specifications and formally verified code in Lean The benchmark comprises of 161 programming problems; it evaluates both formal speci-fication generation and implementation synthesis from natural language, requiring formal correctness proofs for both
|
|
|