Pith. sign in

REVIEW 10 cited by

RARR: Researching and Revising What Language Models Say, Using Language Models

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 2210.08726 v3 pith:T4RF4IXU submitted 2022-10-17 cs.CL cs.AIcs.IRcs.LG

RARR: Researching and Revising What Language Models Say, Using Language Models

classification cs.CL cs.AIcs.IRcs.LG
keywords attributionmodelslanguageoutputrarrgenerationpreservingwhile
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Language models (LMs) now excel at many tasks such as few-shot learning, question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading content. A user cannot easily determine whether their outputs are trustworthy or not, because most LMs do not have any built-in mechanism for attribution to external evidence. To enable attribution while still preserving all the powerful advantages of recent generation models, we propose RARR (Retrofit Attribution using Research and Revision), a system that 1) automatically finds attribution for the output of any text generation model and 2) post-edits the output to fix unsupported content while preserving the original output as much as possible. When applied to the output of several state-of-the-art LMs on a diverse set of generation tasks, we find that RARR significantly improves attribution while otherwise preserving the original input to a much greater degree than previously explored edit models. Furthermore, the implementation of RARR requires only a handful of training examples, a large language model, and standard web search.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution

    cs.CL 2026-07 conditional novelty 6.0

    Cheaper LLM judges match frontier models on citation-quality F1 but differ substantially in false positive and false negative rates, meaning reward signal calibration matters more than model cost.

  2. AI Assistance for Human Review of Default Judgments

    cs.CY 2026-06 unverdicted novelty 6.0

    LLM assistant with citation grounding improves accuracy by 6% and review speed by 25.9% in a simulated study of default judgment review.

  3. ZeroSearch: Incentivize the Search Capability of LLMs without Searching

    cs.CL 2025-05 conditional novelty 6.0

    ZeroSearch simulates search engine interactions via supervised fine-tuning of a retrieval module and curriculum-based RL degradation of document quality, achieving comparable or superior performance to real search eng...

  4. ZeroSearch: Incentivize the Search Capability of LLMs without Searching

    cs.CL 2025-05 unverdicted novelty 6.0

    ZeroSearch uses supervised fine-tuning to create a simulated retrieval module and curriculum-based RL rollouts that degrade document quality to train LLMs on search capabilities without real search API calls.

  5. LIMO: Less is More for Reasoning

    cs.CL 2025-02 unverdicted novelty 6.0

    LIMO achieves 63.3% on AIME24 and 95.6% on MATH500 via supervised fine-tuning on roughly 1% of the data used by prior models, supporting the claim that minimal strategic examples suffice when pre-training has already ...

  6. The Flan Collection: Designing Data and Methods for Effective Instruction Tuning

    cs.AI 2023-01 conditional novelty 6.0

    The Flan Collection demonstrates that task balancing, data enrichment, and mixed prompt training are critical to effective instruction tuning, yielding stronger Flan-T5 models released publicly.

  7. HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs

    cs.CL 2026-05 unverdicted novelty 5.0

    HalluScan benchmark tests hallucination detectors on LLMs, identifies NLI Verification as top performer with 0.88 AUROC, and introduces HalluScore (r=0.41 with humans) plus a routing method for 2x cost savings.

  8. Uncertainty-Aware Web-Conditioned Scientific Fact-Checking

    cs.CL 2026-04 unverdicted novelty 5.0

    An uncertainty-gated fact-checking system decomposes claims atomically, verifies them against context, and selectively searches the web only for uncertain facts, outperforming benchmarks while abstaining on conflicts.

  9. Galactica: A Large Language Model for Science

    cs.CL 2022-11 unverdicted novelty 5.0

    Galactica, a science-specialized LLM, reports higher scores than GPT-3, Chinchilla, and PaLM on LaTeX knowledge, mathematical reasoning, and medical QA benchmarks while outperforming general models on BIG-bench.

  10. HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs

    cs.CL 2026-05 unverdicted novelty 4.0

    HalluScan benchmark evaluates hallucination detection in LLMs, reporting NLI Verification at AUROC 0.88 and introducing HalluScore (r=0.41 with humans) plus Adaptive Detection Routing for 2x cost savings.