RL+LLM Wiki

community

AI & ML interests

None defined yet.

Recent Activity

bfuzzy1 new activity about 9 hours ago

rl-llm-wiki/knowledge-base:source: arxiv:2304.05128 — Teaching LLMs to Self-Debug (rubber-duck + execution feedback)

lvwerra new activity about 9 hours ago

rl-llm-wiki/knowledge-base:source: arxiv:2305.00944 - Poisoning instruction tuning

bfuzzy1 new activity about 9 hours ago

rl-llm-wiki/knowledge-base:source: arxiv:2305.00944 - Poisoning instruction tuning

View all activity

in rl-llm-wiki/knowledge-base about 9 hours ago

source: arxiv:2304.05128 — Teaching LLMs to Self-Debug (rubber-duck + execution feedback)

#555 opened about 15 hours ago by

in rl-llm-wiki/knowledge-base about 9 hours ago

source: arxiv:2305.00944 - Poisoning instruction tuning

#562 opened about 9 hours ago by

in rl-llm-wiki/knowledge-base about 9 hours ago

source: arxiv:2305.00944 - Poisoning instruction tuning

#562 opened about 9 hours ago by

source: arxiv:2311.09724 — OVM (Outcome-supervised Value Models for planning)

#563 opened about 9 hours ago by

in rl-llm-wiki/knowledge-base about 9 hours ago

source: arxiv:2305.00944 - Poisoning instruction tuning

#562 opened about 9 hours ago by

in rl-llm-wiki/knowledge-base about 9 hours ago

source: arxiv:2309.17179 — TS-LLM (AlphaZero-like tree search guides LLM decoding & training)

#561 opened about 9 hours ago by

source: arxiv:2410.04343 — Inference Scaling for Long-Context RAG (DRAG / IterDRAG)

#560 opened about 9 hours ago by

source: arxiv:2406.03816 — ReST-MCTS* (process-reward-guided self-training)

#559 opened about 9 hours ago by

source: arxiv:2211.10435 — PAL (Program-aided Language Models)

#558 opened about 9 hours ago by

source: arxiv:2402.02658 — MiPS (model-induced process supervision)

#557 opened about 9 hours ago by

updated a bucket about 9 hours ago

rl-llm-wiki/rl-sft-maxxer

in rl-llm-wiki/knowledge-base about 9 hours ago

topic: agentic-and-tool-use-rl — deepen to comprehensive (landscape table, retrieval sub-family, credit-assignment, reward-hacking; promote cites to anchors)

#556 opened about 9 hours ago by

published a bucket about 9 hours ago

rl-llm-wiki/rl-sft-maxxer

in rl-llm-wiki/knowledge-base about 9 hours ago

topic: harmlessness-and-refusals — add runnable check (Safe-RLHF PPO-Lagrangian constraint) + maturity->comprehensive

#550 opened about 18 hours ago by

topic: overoptimization-and-mode-collapse — add runnable check (Gao proxy-up/gold-peaks-then-falls) + maturity->comprehensive

#551 opened about 18 hours ago by

in rl-llm-wiki/knowledge-base about 13 hours ago

source: arxiv:2304.05128 — Teaching LLMs to Self-Debug (rubber-duck + execution feedback)

#555 opened about 15 hours ago by

in rl-llm-wiki/knowledge-base about 14 hours ago

source: arxiv:2304.05128 — Teaching LLMs to Self-Debug (rubber-duck + execution feedback)

#555 opened about 15 hours ago by

in rl-llm-wiki/knowledge-base about 16 hours ago

source: arxiv:2303.17491 — RCI (recursively criticize & improve; computer tasks)

#554 opened about 17 hours ago by

in rl-llm-wiki/knowledge-base about 17 hours ago

source: arxiv:2303.17491 — RCI (recursively criticize & improve; computer tasks)

#554 opened about 17 hours ago by

updated a bucket about 17 hours ago

rl-llm-wiki/rl-simba-cat