HowieHwong/MemoHarness
MemoHarness: Agent Harnesses That Learn from Experience
Ph.D. student at Notre Dame | Building Frontier Learning Machine
Repositories
HowieHwong/RiskLab
RiskLab (ACL 2026 Demo): A Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems
HowieHwong/Awareness-in-LLM
HowieHwong/HowieHwong
HowieHwong/inspect_petri
An alignment auditing agent capable of quickly exploring alignment hypothesis
HowieHwong/sde-harness
SDE-Harness (Scientific Discovery Evaluation Framework)
HowieHwong/ProbeLLM
ProbeLLM: Automating Principled Diagnosis of LLM Failures
HowieHwong/arxiv-daily-agent
Arxiv Daily Agent
HowieHwong/TrustLLM
[ICML 2024] TrustLLM: Trustworthiness in Large Language Models
HowieHwong/optimizationproblems
A collection of optimization problems in mathematics
HowieHwong/GameofSloanes
A game to find putatively optimal packings in complex projective space with the goal of proving optimality of as many packings as possible.
HowieHwong/MetaTool
[ICLR'24] MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
HowieHwong/lean-erdos-proofs
Machine-checked Lean 4 proofs of statements from google-deepmind/formal-conjectures
HowieHwong/formal-conjectures
A collection of formalized statements of conjectures in Lean.
HowieHwong/Agentic-Guardian
[ICLR'26] Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
HowieHwong/TrustGPT
Can We Trust Large Language Models?: A Benchmark for Responsible Large Language Models via Toxicity, Bias, and Value-alignment Evaluation
HowieHwong/DataGen
[ICLR'25] DataGen: Unified Synthetic Dataset Generation via Large Language Models
HowieHwong/ChemOrch
[NeurIPS'25] ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions
HowieHwong/ValueLence
ValueLence: A Dashboard for In-Depth Value Probing of LLMs
HowieHwong/Static-to-Dynamic-LLMEval
HowieHwong/TrustEval-toolkit
Toolkit for evaluating the trustworthiness of generative foundation models.
HowieHwong/ObscurePrompt
ObscurePrompt: Jailbreaking Large Language Models via Obscure Input
HowieHwong/LLaMA-Efficient-Tuning
Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA) (LLaMA-2, BLOOM, Falcon, Baichuan)
HowieHwong/llm-misinformation-survey
Paper list for the survey "Combating Misinformation in the Age of LLMs: Opportunities and Challenges" and the initiative "LLMs Meet Misinformation"
HowieHwong/Awesome-LLM-Eval
Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, learderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表，主要面向大型语言模型评测（例如ChatGPT、LLaMA、GLM、Baichuan等）.
HowieHwong/TrustworthyLFM
Related paper on the trustworthiness of large foundation models.
HowieHwong/ChatGPT-Paper-Reading-List
Paper List for ChatGPT