EIT-NLP / AccuracyParadox-RLHF
[EMNLP 2024 Main] Official implementation of the paper "The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models". (by Yanjun Chen)
☆12Updated 3 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for AccuracyParadox-RLHF
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆36Updated 8 months ago
- Self-Supervised Alignment with Mutual Information☆14Updated 5 months ago
- ☆27Updated 8 months ago
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆46Updated 4 months ago
- Official Implementation for the paper "Integrative Decoding: Improving Factuality via Implicit Self-consistency"☆17Updated last month
- The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism☆25Updated 3 months ago
- PyTorch implementation of experiments in the paper Aligning Language Models with Human Preferences via a Bayesian Approach☆30Updated last year
- [ACL 2024] Code for the paper "ALaRM: Align Language Models via Hierarchical Rewards Modeling"☆24Updated 7 months ago
- ☆29Updated 2 weeks ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆39Updated 3 months ago
- [ACL 2024] Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning☆30Updated 3 months ago
- The official repository of "Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint"☆32Updated 10 months ago
- [EMNLP 2024 Main] Official implementation of the paper "Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mech…☆11Updated last month
- [NAACL 2024] A Synthetic, Scalable and Systematic Evaluation Suite for Large Language Models☆32Updated 5 months ago
- [ACL 2024] Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models☆14Updated 4 months ago
- ☆26Updated 8 months ago
- [NeurIPS 2022] Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddings☆20Updated last year
- ☆14Updated 2 years ago
- Code and data for "Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue" (ACL 2024)☆21Updated 3 months ago
- Conic10K: A large-scale dataset for closed-vocabulary math problem understanding. Accepted to EMNLP2023 Findings.☆23Updated 11 months ago
- Domain-specific preference (DSP) data and customized RM fine-tuning.☆24Updated 8 months ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆24Updated 6 months ago
- Code for "Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective"☆29Updated 6 months ago
- Benchmarking Benchmark Leakage in Large Language Models☆44Updated 5 months ago
- ☆11Updated 11 months ago
- ☆22Updated 2 months ago
- ☆14Updated 8 months ago
- Code of the COLING22 paper "uChecker: Masked Pretrained Language Models as Unsupervised Chinese Spelling Checkers"☆18Updated 2 years ago
- [NeurIPS 2023] Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective☆29Updated last year
- [EMNLP 2023] Once Upon a *Time* in *Graph*: Relative-Time Pretraining for Complex Temporal Reasoning☆18Updated last year