Z1zs / MMNeuronLinks
Official implementation of "MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model". Our codes are borrowed from Tang's language specific neurons implementation and nrimsky's logit lens implementation.
☆25Updated last year
Alternatives and similar repositories for MMNeuron
Users that are interested in MMNeuron are comparing it to the libraries listed below
Sorting:
- ☆69Updated 10 months ago
- Official code for our paper "Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models"☆20Updated 2 months ago
- Public code repo for COLING 2025 paper "Aligning LLMs with Individual Preferences via Interaction"☆41Updated 9 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆62Updated last year
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆85Updated last year
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆76Updated 7 months ago
- [ACL 2025 Findings] Official implementation of the paper "Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning".☆21Updated 11 months ago
- Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."☆51Updated last year
- Code for ACL 2024 paper "Soft Self-Consistency Improves Language Model Agents"☆25Updated last year
- [ICLR 2024] This is the repository for the paper titled "DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning"☆101Updated last year
- Official Code Repository for the paper "Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-intensive Tasks…☆42Updated last year
- [2025-TMLR] A Survey on the Honesty of Large Language Models☆64Updated last year
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆49Updated last year
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆46Updated last year
- FeatureAlignment = Alignment + Mechanistic Interpretability☆34Updated 10 months ago
- ☆141Updated 10 months ago
- [NAACL 2024] Vision language model that reduces hallucinations through self-feedback guided revision. Visualizes attentions on image feat…☆47Updated last year
- Code for Heima☆59Updated 9 months ago
- [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style☆73Updated 6 months ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"☆93Updated last year
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆88Updated last year
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆71Updated 6 months ago
- Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue (ACL 2024)☆24Updated 3 months ago
- [ICLR '25] Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations"☆96Updated last month
- Code for Reducing Hallucinations in Vision-Language Models via Latent Space Steering☆102Updated last year
- Large Language Models Can Self-Improve in Long-context Reasoning☆72Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆69Updated last week
- Code for ACL 2024 accepted paper titled "SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language …☆38Updated last year
- A curated list of resources for activation engineering☆121Updated 3 months ago
- [ICLR 2025] Pad: Personalized alignment of llms at decoding-time☆18Updated 10 months ago