REVIEW 10 cited by
Self-Alignment with Instruction Backtranslation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We present a scalable method to build a high quality instruction following language model by automatically labelling human-written text with corresponding instructions. Our approach, named instruction backtranslation, starts with a language model finetuned on a small amount of seed data, and a given web corpus. The seed model is used to construct training examples by generating instruction prompts for web documents (self-augmentation), and then selecting high quality examples from among these candidates (self-curation). This data is then used to finetune a stronger model. Finetuning LLaMa on two iterations of our approach yields a model that outperforms all other LLaMa-based models on the Alpaca leaderboard not relying on distillation data, demonstrating highly effective self-alignment.
Forward citations
Cited by 10 Pith papers
-
HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs
HSS-Synth generates 230k instruction-tuning samples for 14 humanities/social-science fields and reports state-of-the-art fine-tuning results on 16 benchmarks.
-
Bridging Offline and Online Reinforcement Learning for LLMs
Semi-online DPO, which syncs the generation model every few update steps, performs nearly as well as fully online DPO and GRPO, while strongly beating offline DPO.
-
Aligning Large Language Models with Implicit Preferences from User-Generated Content
PUGC turns unlabeled user-generated content into preference pairs by scoring policy responses against the source post as a reference, reaching 35.93% length-controlled win rate on AlpacaEval 2.0 with Mistral-7B-Instruct.
-
From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding
A 1M-instruction dataset, generated by attributing real instructions to documents, users and motivations and then reversing the process over web documents, improves instruction-following benchmarks for 7B-14B models.
-
Can Structured Templates Facilitate LLMs in Tackling Harder Tasks? : An Exploration of Scaling Laws by Difficulty
Training on easy synthetic math data lowers accuracy on hard benchmarks, and the proposed SST framework, which teaches explicit procedural chains, aims to reverse that drop.
-
Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future
Anchoring rejected responses to the initial model and choosing responses from a future model raises AlpacaEval 2.0 win rate from 19.69 to 29.44 for Llama3.1-8B.
-
An Uncertainty-Driven Adaptive Self-Alignment Framework for Large Language Models
A training pipeline that scores a model's own responses for semantic, factual, and safety uncertainty, builds preference pairs from those scores, and trains in three difficulty stages improves reported alignment score...
-
ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models
ALPS selects task-sensitive attention heads by measuring Wasserstein distance between base and task-tuned weights, and freezing other heads during fine-tuning improves performance and efficiency.
-
Mixtures of SubExperts for Large Language Continual Learning
MoSEs combines task-specific prompts, keys, and sparse low-rank subexpert masks with a router to cut catastrophic forgetting in sequential LLM fine-tuning.
-
Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
ACBench tests compressed LLMs on agentic tasks and finds 4-bit quantization keeps tool use and workflow generation strong while hurting real-world application performance.
Discussion (0). Sign in to comment.