Pith. sign in

REVIEW 11 cited by

Orca 2: Teaching Small Language Models How to Reason

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

arxiv 2311.11045 v2 pith:JXUTRQVT submitted 2023-11-18 cs.AI

classification cs.AI
keywords modelsorcasmallerdifferentlargermodelreasoningsmall
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Orca 1 learns from rich signals, such as explanation traces, allowing it to outperform conventional instruction-tuned models on benchmarks like BigBench Hard and AGIEval. In Orca 2, we continue exploring how improved training signals can enhance smaller LMs' reasoning abilities. Research on training small LMs has often relied on imitation learning to replicate the output of more capable models. We contend that excessive emphasis on imitation may restrict the potential of smaller models. We seek to teach small LMs to employ different solution strategies for different tasks, potentially different from the one used by the larger model. For example, while larger models might provide a direct answer to a complex task, smaller models may not have the same capacity. In Orca 2, we teach the model various reasoning techniques (step-by-step, recall then generate, recall-reason-generate, direct answer, etc.). More crucially, we aim to help the model learn to determine the most effective solution strategy for each task. We evaluate Orca 2 using a comprehensive set of 15 diverse benchmarks (corresponding to approximately 100 tasks and over 36,000 unique prompts). Orca 2 significantly surpasses models of similar size and attains performance levels similar or better to those of models 5-10x larger, as assessed on complex tasks that test advanced reasoning abilities in zero-shot settings. make Orca 2 weights publicly available at aka.ms/orca-lm to support research on the development, evaluation, and alignment of smaller LMs

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 30 citations worldwide. Full citation record

  1. Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability

    cs.CL 2025-05 conditional novelty 7.0 of 10

    Rationale-augmented finetuning can hurt accuracy while improving calibration, with the sizes of both effects tied linearly to task difficulty.

  2. PertReason: A Knowledge-Grounded Benchmark and Framework for Cell-State-Conditioned Mechanistic Reasoning of Perturbation Effects

    cs.LG 2026-07 conditional novelty 6.0 of 10

    PertReasonQA scores AI models on cell-state-conditioned mechanistic reasoning about perturbation effects, and PertReasonLM, trained with reasoning supervision, reaches 0.736 balanced accuracy and 0.976 edge recall ver...

  3. GLAN-QnA-KR: A Seedless Taxonomy-Driven Korean Instruction Corpus

    cs.CL 2026-05 conditional novelty 6.0 of 10

    A 303,581-row Korean instruction corpus generated seedlessly from a 1,084-discipline taxonomy, with near-zero duplicates and low measured overlap with KMMLU, KoBEST, and HAE-RAE-Bench.

  4. Predict-then-Diffuse: Adaptive Response Length for Compute-Budgeted Inference in Diffusion LLMs

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Predict-then-Diffuse predicts response lengths for diffusion LLMs via an auxiliary model and safety buffer to reduce FLOP waste while preserving output quality.

  5. On the Effect of Instruction Tuning Loss on Generalization

    cs.CL 2025-07 conditional novelty 6.0 of 10

    Weighted Instruction Tuning, with low-to-moderate prompt weight and moderate-to-high response weight, beats the standard response-only instruction tuning loss in most of the 75 (model, dataset, benchmark) settings tested.

  6. SynthEHR-Eviction: Enhancing Eviction SDoH Detection with LLM-Augmented Synthetic EHR Data

    cs.CL 2025-07 conditional novelty 6.0 of 10

    An LLM-augmented synthetic data pipeline produces the largest public eviction-focused SDoH dataset (14 categories) and fine-tuned open LLMs that outperform prompt-optimized GPT-4o on the authors' test sets.

  7. Toward Cybersecurity-Expert Small Language Models

    cs.CL 2025-10 conditional novelty 5.0 of 10

    A family of 4B–20B cybersecurity models fine-tuned on an enriched, expert-steered reasoning dataset matches or beats larger frontier models on core CTI benchmarks.

  8. VERA: Variational Inference Framework for Jailbreaking Large Language Models

    cs.CR 2025-06 conditional novelty 5.0 of 10

    VERA frames black-box jailbreaking as variational inference, training a LoRA-tuned attacker that samples diverse fluent prompts; reported ASRs are high but several evaluation choices weaken the SOTA claims.

  9. SLMEval: Entropy-Based Calibration for Human-Aligned Evaluation of Large Language Models

    cs.CL 2025-05 reject novelty 5.0 of 10

    SLMEval fits a latent strength distribution to human preferences by maximum entropy and uses it to reweight LLM judge scores, reporting stronger correlation with human judgment on two production tasks.

  10. From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI

    cs.AI 2026-06 conditional novelty 4.0 of 10

    Autonomous AI becomes dependable when tool use is embedded in persistent workspaces with reusable skills, shifting evaluation from answers to task closure.

  11. Cross-lingual Aspect-Based Sentiment Analysis: A Survey on Tasks, Approaches, and Challenges

    cs.CL 2025-08 conditional novelty 4.0 of 10

    A comprehensive survey of cross-lingual aspect-based sentiment analysis that catalogs tasks, datasets, modeling paradigms, and cross-lingual transfer techniques, and identifies research gaps.

Pith tools