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.
arXiv preprint arXiv:2202.05144 , year=
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Self-generated QA supervision for language models is fragile due to non-uniform question selection and instruction compliance during answering, with mitigations that reduce compliance from 88% to 13%.
UnIte selects target-domain documents for pseudo-query generation by filtering high aleatoric uncertainty and prioritizing high epistemic uncertainty, yielding +2.45 to +3.49 nDCG@10 gains on BEIR with ~4k samples.
SPECTRA generates reproducible synthetic IR corpora up to 60,000 documents with controllable distractors, long-tail vocabulary, and graded relevance labels via a single-process Python prototype.
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.
ARHN refines hard-negative training data for dense retrieval by using LLMs to convert answer-containing passages into additional positives and exclude answer-containing passages from the negative set.
Empirical comparison across 14 retrievers on the BRIGHT benchmark shows reasoning-specialized models can match strong accuracy with competitive speed while many large LLM bi-encoders add latency for small gains and confidence scores remain poorly calibrated.
RankFlow deploys four LLM roles in sequence to rewrite queries, generate pseudo-answers, summarize passages, and rerank candidates, outperforming prior methods on TREC-DL, BEIR, and NovelEval.
Empirical study of RLAIF for portable query generation finds reward shaping controls performance more than optimizer choice and a rule-based reward floor yields +0.147 quality gain.
RAG-Match is a three-stage framework for semantic relevance modeling that integrates knowledge-augmented pretraining, hierarchical reasoning alignment, and preference-based decision calibration, outperforming LLM baselines on a search benchmark.
The paper introduces a seed-guided contrastive framework that uses LLMs to generate realistic synthetic queries and topicality labels for cold-start natural language search, outperforming no-seed and InPars baselines on realism metrics and producing harder evaluation sets.
A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler.
citing papers explorer
-
CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges
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.
-
Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA
Self-generated QA supervision for language models is fragile due to non-uniform question selection and instruction compliance during answering, with mitigations that reduce compliance from 88% to 13%.
-
UnIte: Uncertainty-based Iterative Document Sampling for Domain Adaptation in Information Retrieval
UnIte selects target-domain documents for pseudo-query generation by filtering high aleatoric uncertainty and prioritizing high epistemic uncertainty, yielding +2.45 to +3.49 nDCG@10 gains on BEIR with ~4k samples.
-
SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics
SPECTRA generates reproducible synthetic IR corpora up to 60,000 documents with controllable distractors, long-tail vocabulary, and graded relevance labels via a single-process Python prototype.
-
Assisted Counterspeech Writing at the Crossroads of Hate Speech and Misinformation
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.
-
ARHN: Answer-Centric Relabeling of Hard Negatives with Open-Source LLMs for Dense Retrieval
ARHN refines hard-negative training data for dense retrieval by using LLMs to convert answer-containing passages into additional positives and exclude answer-containing passages from the negative set.
-
Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead
Empirical comparison across 14 retrievers on the BRIGHT benchmark shows reasoning-specialized models can match strong accuracy with competitive speed while many large LLM bi-encoders add latency for small gains and confidence scores remain poorly calibrated.
-
RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models
RankFlow deploys four LLM roles in sequence to rewrite queries, generate pseudo-answers, summarize passages, and rerank candidates, outperforming prior methods on TREC-DL, BEIR, and NovelEval.
-
Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job Search
Empirical study of RLAIF for portable query generation finds reward shaping controls performance more than optimizer choice and a rule-based reward floor yields +0.147 quality gain.
-
RAG-Match: Retrieval-Augmented Knowledge Injection and Hierarchical Reasoning for Calibrated Semantic Relevance
RAG-Match is a three-stage framework for semantic relevance modeling that integrates knowledge-augmented pretraining, hierarchical reasoning alignment, and preference-based decision calibration, outperforming LLM baselines on a search benchmark.
-
Bridging the Cold-Start Gap: LLM-Powered Synthetic Data Generation for Natural Language Search at Airbnb
The paper introduces a seed-guided contrastive framework that uses LLMs to generate realistic synthetic queries and topicality labels for cold-start natural language search, outperforming no-seed and InPars baselines on realism metrics and producing harder evaluation sets.
-
A Survey on Knowledge Distillation of Large Language Models
A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler.