Challenge: Recent research on test-time adaptation suggests a possible way to improve the generalization ability of LLMs.
Approach: They propose to use multi-armed bandit learning and multi-arm dueling bandits to solve a multi-source test-time model adaptation problem from user feedback.
Outcome: The proposed model is more effective than other strong baselines on extractive question answering datasets.

Similar Papers

Simulating Bandit Learning from User Feedback for Extractive Question Answering (2022.acl-long)

Copied to clipboard

Challenge: Explicit feedback from users can be used to continually improve system performance.
Approach: They study the potential of learning from user feedback for extractive question answering by simulating feedback using supervised data.
Outcome: The proposed model improves on a few examples and can be deployed in new domains without any data annotation effort.
Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to audit Large Language Models (LLMs) lack mechanisms to efficiently adapt to model-specific vulnerabilities at inference.
Approach: They propose a red-teaming framework that adapts online to identify and exploit model failure modes under distinct attack styles.
Outcome: The proposed framework outperforms state-of-the-art methods on AdvBench and HarmBench, while generating more human-readable adversarial prompts (lower perplexity).
SEMQA: Semi-Extractive Multi-Source Question Answering (2024.naacl-long)

Copied to clipboard

Challenge: Recent proposed long-form question answering systems have shown promising capabilities, but attributing and verifying their generated abstractive answers can be difficult.
Approach: They propose a task that summarises multiple sources in a semi-extractive fashion . they create a dataset with human-written semi-extractive answers to natural and generated questions .
Outcome: The proposed task summarizes multiple sources in a semi-extractive fashion and produces fine in-line attributions by-design that are easy to verify, interpret, and evaluate.
Continually Improving Extractive QA via Human Feedback (2023.emnlp-main)

Copied to clipboard

Challenge: a study of extractive question answering systems using human feedback shows promising potential for continual learning.
Approach: They study extractive question answering system by using user feedback to improve it . they design and deploy an iterative approach where users ask questions and provide feedback .
Outcome: The proposed model improves over time across different data regimes and domains . human user feedback is more affordable and abundant than annotations provided by trained experts .
Test-Time Self-Adaptive Small Language Models for Question Answering (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent instruction-finetuned large language models (LMs) have shown notable performances in various tasks, such as question-answering.
Approach: They propose to use unlabeled test data to transfer smaller language models with limited knowledge.
Outcome: The proposed strategy shows significant performance improvements on benchmark QA datasets with higher robustness across diverse prompts, enabling LMs to stay stable.
Bandits Don’t Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits (2021.findings-emnlp)

Copied to clipboard

Challenge: Training data for machine translation (MT) is often sourced from multiple large corpora that are multi-faceted in nature.
Approach: They propose to optimize the balance between translationese and natural training data to relieve system developers from manual schedule design.
Outcome: The proposed model relieves system developers from manual schedule design.
Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to visual question answering (VQA) are not suitable for real-world applications.
Approach: They propose a supervised multi-modal domain adaptation method for visual question answering in images that exploits supervised domain adaptation.
Outcome: The proposed method outperforms state-of-the-art methods on the benchmark VQA 2.0 and VizWiz datasets.
Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answering (2022.coling-1)

Copied to clipboard

Challenge: Generative question answering (QA) models generate answers to complex questions, but their mechanism for doing so is still poorly understood.
Approach: They decompose multi-hop questions into multiple corresponding single-hop question chains and find marked inconsistency in QA models’ answers on these pairs of ostensibly identical question chains.
Outcome: The proposed models lack zero-shot multi-hop reasoning ability when trained on single-hop questions and on logical forms.
Generalizing Question Answering System with Pre-trained Language Model Fine-tuning (D19-58)

Copied to clipboard

Challenge: Existing methods focus on improving in-domain performance, leaving open the question of how they can generalize to out-of-domain and unseen RC tasks.
Approach: They propose a multi-task learning framework that learns the shared representation across different tasks and builds on a large pre-trained language model and fine-tuned on multiple RC datasets.
Outcome: The proposed framework improves the BERT-Large baseline by 8.39 and 7.22 respectively.
Source-Free Unsupervised Domain Adaptation for Question Answering via Prompt-Assisted Self-learning (2024.findings-naacl)

Copied to clipboard

Challenge: Existing SFDA methods focus on the adaptation phase, overlooking the impact of source domain training on model generalizability.
Approach: They propose a source-free domain adaptation approach for Question Answering where a model trained on a domain is adapted to unlabeled target domains without additional source data.
Outcome: The proposed model outperforms existing methods in managing domain gaps and demonstrating greater stability across target domains.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations