Pith. sign in

REVIEW 5 cited by

Reframing Human-AI Collaboration for Generating Free-Text Explanations

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 2112.08674 v2 pith:6JXBXJEB submitted 2021-12-16 cs.CL

Reframing Human-AI Collaboration for Generating Free-Text Explanations

classification cs.CL
keywords explanationsacceptabilitygeneratingmodelsfilterfree-textgpt-3higher
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large language models are increasingly capable of generating fluent-appearing text with relatively little task-specific supervision. But can these models accurately explain classification decisions? We consider the task of generating free-text explanations using human-written examples in a few-shot manner. We find that (1) authoring higher quality prompts results in higher quality generations; and (2) surprisingly, in a head-to-head comparison, crowdworkers often prefer explanations generated by GPT-3 to crowdsourced explanations in existing datasets. Our human studies also show, however, that while models often produce factual, grammatical, and sufficient explanations, they have room to improve along axes such as providing novel information and supporting the label. We create a pipeline that combines GPT-3 with a supervised filter that incorporates binary acceptability judgments from humans in the loop. Despite the intrinsic subjectivity of acceptability judgments, we demonstrate that acceptability is partially correlated with various fine-grained attributes of explanations. Our approach is able to consistently filter GPT-3-generated explanations deemed acceptable by humans.

discussion (0)

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

Forward citations

Cited by 5 Pith papers

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

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

    cs.CL 2022-01 accept novelty 9.0

    Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.

  2. CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges

    cs.CL 2026-06 unverdicted novelty 8.0

    Presents a new expert-curated dataset of multi-turn counterspeech dialogues in five languages targeting hate against seven groups, with span annotations linking to verified external knowledge for RAG applications.

  3. Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation

    cs.CL 2026-05 conditional novelty 6.0

    LLMs generate adequate counterspeech for co-occurring hate and misinformation in 40% of cases, with a mixed knowledge strategy from fact-checkers and NGOs proving most effective after expert revision.

  4. A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization

    cs.CL 2026-06 unverdicted novelty 5.0

    A single LLM rewrite of skill descriptions using false positive and negative cases matches manual optimization performance in production, with most other pipeline components adding little value.

  5. EduCoder: An Open-Source Annotation System for Education Transcript Data

    cs.CL 2025-07 accept novelty 3.0

    EduCoder supplies a collaborative annotation platform specialized for education transcripts that supports complex codebook definition, mixed annotation types, contextual materials, and inter-annotator comparison.