tsinghua-fib-lab / Token_SignatureLinks
This repository contains the core implementation of our ICML 2025 paper: "Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models."
☆41Updated 5 months ago
Alternatives and similar repositories for Token_Signature
Users that are interested in Token_Signature are comparing it to the libraries listed below
Sorting:
- Collecting personality-indicative data for role-playing agents.☆23Updated 10 months ago
- SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation☆57Updated 8 months ago
- Official Code of Logits-Based-Finetuning☆91Updated 6 months ago
- [ICML 2025] Official implementation of paper "Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning"☆49Updated 6 months ago
- [ACL 2025 main] SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Mode…☆39Updated 4 months ago
- A comprehensive collection of resources focused on addressing and understanding hallucination phenomena in MLLMs.☆35Updated last year
- [NeurIPS 2025] Hybrid Latent Reasoning via Reinforcement Learning☆166Updated 3 months ago
- SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models☆39Updated 10 months ago
- [ICLR 25] The implementation of paper Diff-Prompt: Diffusion-Driven Prompt Generator with Mask Supervision.☆52Updated 5 months ago
- This tool(enhance_long) aims to enhance the LlaMa2 long context extrapolation capability in the lowest-cost approach, preferably without …☆45Updated 2 years ago
- [ICLR 2025] Official implementation of paper "Improving Data Efficiency via Curating LLM-Driven Rating Systems"☆100Updated 9 months ago
- [COLING Demos 2025] an Easy-to-use Tool for Comprehensive Response Evaluation of LLMs☆38Updated 9 months ago
- RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response☆42Updated last year
- Code of Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Ne…☆28Updated last year
- ☆52Updated last year
- Code and datasets for the paper "Bridging Neural and Symbolic Representations with Transitional Dictionary Learning".☆47Updated last year
- ACL 2024☆35Updated 5 months ago
- Rethinking Video-Text Understanding Retrieval from Counterfactually Augmented Data☆38Updated last year
- [EMNLP 2024 Findings] Official PyTorch Implementation of "Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Ge…☆41Updated 10 months ago
- AnomalyControl: Learning Cross-modal Semantic Features for Controllable Anomaly Synthesis☆41Updated 4 months ago
- [ACL 2023 findings] Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization☆17Updated 2 years ago
- [NeurIPS 25 @ ER] Long-Context Modeling with Dynamic Hierarchical Sparse Attention for On-Device LLMs☆73Updated last month
- ☆52Updated 4 months ago
- An Extensible Framework for Retrieval-Augmented LLM Applications: Learning Relevance Beyond Simple Similarity.☆41Updated last year
- An official Project related to Paper "Perceiving Ambiguity and Semantics without Recognition: An Efficient and Effective Ambiguous Scene …☆21Updated 2 years ago
- Public code repository for "Scaling External Knowledge Input Beyond the Context Length of LLMs via Multi-Agent Collaboration"☆20Updated 5 months ago
- Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward☆42Updated last month
- ☆44Updated last year
- StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving☆21Updated last year
- Our imbalance-aware ViT model achieves 0.91035 accuracy on the public leaderboard and 0.87750 on the private leaderboard of the ML2022Spr…☆26Updated 6 months ago