[COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free
☆62Apr 6, 2025Updated last year
Alternatives and similar repositories for SEAL
Users that are interested in SEAL are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [EMNLP 25] An effective and interpretable weight-editing method for mitigating overly short reasoning in LLMs, and a mechanistic study un…☆19Dec 17, 2025Updated 7 months ago
- ☆19Sep 16, 2025Updated 10 months ago
- Code for SafeMERGE (ICLR 2025).☆15Apr 1, 2025Updated last year
- [NeurIPS 2025] The implementation of paper "The Emergence of Abstract Thought in Large Language Models Beyond Any Language"☆20Jun 9, 2025Updated last year
- [NeurIPS 2025] The implementation of paper "On Reasoning Strength Planning in Large Reasoning Models"☆31Jul 6, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [NeurIPS 2025@FoRLM] R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search☆17Jan 24, 2026Updated 6 months ago
- ☆15Nov 7, 2024Updated last year
- ☆15Feb 26, 2025Updated last year
- ☆14May 13, 2022Updated 4 years ago
- ☆19Aug 4, 2025Updated last year
- ☆19Jun 21, 2025Updated last year
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆75Oct 2, 2025Updated 10 months ago
- DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails☆34Feb 26, 2025Updated last year
- ☆18Aug 19, 2024Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- A Unified Framework for High-Performance and Extensible LLM Steering☆289Updated this week
- Codebase for layer wise N:M pruning pattern assignment for LLMs☆15Aug 5, 2025Updated last year
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆19Oct 21, 2024Updated last year
- [NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient☆67Sep 27, 2025Updated 10 months ago
- Official implementation of Latent-SFT: teaching LLMs to reason with vocabulary-space latent chains.☆58May 18, 2026Updated 2 months ago
- ☆24Dec 8, 2024Updated last year
- [ICLR 2026] The implementation of paper "AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint"☆62Nov 20, 2025Updated 8 months ago
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆50Jul 28, 2024Updated 2 years ago
- [ACL'26 Findings] Steering LLM Thinking with Budget Guidance☆34Feb 19, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆211Mar 12, 2026Updated 4 months ago
- The official implementation for "Mitigating Overthinking in Large Reasoning Models via Manifold Steering"☆15May 29, 2025Updated last year
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆49Oct 10, 2024Updated last year
- [ICLR 2025] On Evluating the Durability of Safegurads for Open-Weight LLMs☆13Jun 20, 2025Updated last year
- [COLM 2026] Resa: Transparent Reasoning Models via SAEs☆49Sep 23, 2025Updated 10 months ago
- [ICLR 2025] FLAT: LLM Unlearning via Loss Adjustment with Only Forget Data☆14Feb 26, 2025Updated last year
- [AAAI26] Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilitie…☆11Feb 7, 2026Updated 6 months ago
- ☆22May 23, 2025Updated last year
- Code for “SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation(ICLR 2025)”☆29Oct 23, 2025Updated 9 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆51Jan 15, 2026Updated 6 months ago
- ☆22May 14, 2026Updated 2 months ago
- ☆28Jul 18, 2025Updated last year
- ☆56Jul 7, 2025Updated last year
- [EMNLP 2025 Main] AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time☆89Jun 10, 2025Updated last year
- [ICML25] Official repo for "Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond…☆24Sep 27, 2025Updated 10 months ago
- ☆48Sep 29, 2024Updated last year