mlsanityData to 7 Oct 2026

CorrectionLM: Self-Corrections with SLM for Dialogue State Tracking

arXiv 2410.18209 ↗First posted 23 Oct 2024cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have demonstrated self-improvement capabilities via feedback and refinement, but current small language models (SLMs) have had limited success in this area. Existing correction approaches often rely on distilling knowledge from LLMs, which imposes significant computation demands. In this work, we introduce CORRECTIONLM, a novel correction framework that enables SLMs to self-correct using in-context exemplars without LLM involvement. Applied to two dialogue state tracking (DST) tasks in low-resource settings, CORRECTIONLM achieves results similar to a state-of-the-art LLM at a small fraction of the computation costs.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 36 of its 46 references that are in the map. First posted on arXiv 23 Oct 2024.

Builds on

36 of 46 references.

References · 36

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  5. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  6. 2023Teaching Large Language Models to Self-Debugcited by 963
  7. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  8. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  9. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  10. 2022Large Language Models Can Self-Improvecited by 656
  11. 2021MetaICL: Learning to Learn In Contextcited by 450
  12. 2022Self-critiquing models for assisting human evaluatorscited by 372
24 more
  1. 2023Language Models can Solve Computer Taskscited by 371
  2. 2022CodeT: Code Generation with Generated Testscited by 369
  3. 2020A Simple Language Model for Task-Oriented Dialoguecited by 331
  4. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 297
  5. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
  6. 2022Generating Sequences by Learning to Self-Correctcited by 271
  7. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  8. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 215
  9. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 203
  10. 2021Meta-learning via Language Model In-context Tuningcited by 163
  11. 2022Distilling Reasoning Capabilities into Smaller Language Modelscited by 155
  12. 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?cited by 153
  13. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  14. 2023RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputscited by 104
  15. 2021Dialogue State Tracking with a Language Model using Schema-Driven Promptingcited by 94
  16. 2021MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluationcited by 86
  17. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  18. 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
  19. 2021Zero-shot Generalization in Dialog State Tracking through Generative Question Answeringcited by 33
  20. 2023Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue Systemcited by 30
  21. 2023Teaching Language Models to Self-Improve through Interactive Demonstrationscited by 26
  22. 2023OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Trackingcited by 17
  23. 2020Improving Limited Labeled Dialogue State Tracking with Self-Supervisioncited by 16
  24. 2022Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performancescited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026AVERT: Audio-Verified Adjudication for Spoken Dialogue State Trackingcited by 0