Paper Citation Record · LEDGER

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization

As of 14 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 1 inbound Pith citation observation for arXiv:2412.15453.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2412.15453 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T11:27:55.334090Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T23:55:12.149307Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T23:55:12.182092Z

Reference resolution

16 of 16 outbound references displayed

verified exact0
verified fuzzy5
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 060fe410-6472-4a02-8902-dca6509f9a02 · outbound

This paper cites The Llama 3 Herd of Models.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization The Llama 3 Herd of Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T11:27:55.283354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b5c118b-d62f-49bd-a617-755acf9fa8af · outbound

This paper cites Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-08-11T11:27:55.448210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f9dcf0be-8f1c-4e25-9f19-fca5afb0cfaa · outbound

This paper cites Outcome-Constrained Large Language Models for Countering Hate Speech.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization Outcome-Constrained Large Language Models for Countering Hate Speech

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T11:27:55.290769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b17e97c-ca98-48ed-852a-72f3c4a640ed · outbound

This paper cites On Zero-Shot Counterspeech Generation by LLMs.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization On Zero-Shot Counterspeech Generation by LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T11:27:55.307040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3886aff7-f3a9-4947-9346-ec87272b59ea · outbound

This paper cites an unresolved cited work.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:27:55.490180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c15e0c04-c073-4f3d-a562-6d40d652936b · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T11:27:55.318878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8523222d-a54c-4b7f-9ddf-8cee7b453f6a · outbound

This paper cites Procesamiento del lenguaje natu- ral, 71:371–381.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization Procesamiento del lenguaje natu- ral, 71:371–381

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:27:55.479718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f792569f-db16-4d48-a52e-b70ca49ceea6 · outbound

This paper cites In Findings of the Association for Computational Linguistics: EMNLP 2021 , pages 2127–2137, Punta Cana, Dominican Republic.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization In Findings of the Association for Computational Linguistics: EMNLP 2021 , pages 2127–2137, Punta Cana, Dominican Republic

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:27:55.469292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dc2011f7-34cd-4447-b503-0d5c98efe2c3 · outbound

This paper cites BERTScore: Evaluating Text Generation with BERT.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization BERTScore: Evaluating Text Generation with BERT

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T11:27:55.330191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43debb04-e933-4a49-bbb8-ec98e5f09418 · outbound

This paper cites A LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization A LLM-Based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T11:27:55.334090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bea2532-1df6-40fb-93d2-1a82c9f86cb6 · outbound

This paper cites Release Strategies and the Social Impacts of Language Models.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization Release Strategies and the Social Impacts of Language Models

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-11T11:27:55.311084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05964936-4480-4d34-8482-d39a27770b2e · outbound

This paper cites Hope Speech Detection: A Computational Analysis of the Voice of Peace.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization Hope Speech Detection: A Computational Analysis of the Voice of Peace

Reference 2020

Resolution: metadata mismatch; local_arxiv, observed 2026-08-11T11:27:55.415543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9d4271f4-bc0f-4a8d-8b1e-a5c7fa4f397d · outbound

This paper cites In Find- ings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 899–914, Online.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization In Find- ings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 899–914, Online

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:27:55.512142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b020919a-50f4-4190-a6be-3be160d4ed7e · outbound

This paper cites Training language models to follow instructions with human feedback.

Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization Training language models to follow instructions with human feedback

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T11:27:55.298599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb95973a-a240-4cda-9192-35ce2f9c13e3 · outbound

This paper cites In Find- ings of the Association for Computational Linguis- tics: EMNLP 2023 , pages 9759–9777, Singapore.

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:27:55.501587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6a52bebd-4124-48fe-b798-2744016e0c87 · outbound

This paper cites In Find- ings of the Association for Computational Linguis- tics: NAACL 2024, pages 3480–3499, Mexico City, Mexico.

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:27:55.523516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation 9f52c7e5-8477-4cba-8984-c5570d50057d · inbound

Can NLP Tackle Hate Speech in the Real World? Stakeholder-Informed Feedback and Survey on Counterspeech cites this paper.

Can NLP Tackle Hate Speech in the Real World? Stakeholder-Informed Feedback and Survey on Counterspeech Northeastern Uni at Multilingual Counterspeech Generation: Enhancing Counter Speech Generation with LLM Alignment through Direct Preference Optimization

Reference 2024

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T23:55:12.187414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.