Challenge: Existing dataset inference methods require logit access, but many modern LLMs restrict such access.
Approach: They propose a token-only dataset inference framework that allows models to overwrite prior knowledge when trained on new data.
Outcome: The proposed framework overwrites prior knowledge when trained on new data.

Similar Papers

Self-training Large Language Models through Knowledge Detection (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) often require extensive labeled datasets and training compute to achieve impressive performance across downstream tasks.
Approach: They propose a self-training paradigm where the LLM curates its own labels and selectively trains on unknown data samples identified through a reference-free consistency method.
Outcome: The proposed model reduces the dependency on large labeled datasets and mitigates catastrophic forgetting in out-of-distribution benchmarks.
Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training (2025.findings-acl)

Copied to clipboard

Challenge: Existing defenses for large language models do not account for the sequential nature of text data.
Approach: They propose a lightweight yet effective empirical privacy defense that leverages token-specific characteristics to protect training data of large language models.
Outcome: The proposed approach provides strong protection against membership inference attacks and improves language modeling performance by 10% across different LLM architectures and datasets compared to baselines.
OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) trained over corpora risk memorizing sensitive, copyrighted, or toxic content.
Approach: They propose a framework that removes targeted data while preserving model utility.
Outcome: The proposed framework resists membership inference attacks, minimizes impact on retained data, and maintains robustness across diverse scenarios.
Exploring the Hidden Capacity of LLMs for One-Step Text Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) can reconstruct surprisingly long texts via autoregressive generation from just one trained input embedding.
Approach: They show that large language models can reconstruct surprisingly long texts via autoregressive generation from just one trained input embedding.
Outcome: The proposed model can generate hundreds of accurate tokens in one token-parallel forward pass, when provided with only two learned embeddings.
Harnessing Large Language Models as Post-hoc Correctors (2024.findings-acl)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have demonstrated their effectiveness in a wide range of tasks, including machine translation and commonsense reasoning.
Approach: They propose a training-free framework that can work as a post-hoc corrector to propose corrections for ML models.
Outcome: The proposed framework improves the performance of a number of models by up to 39% on text analysis and the challenging molecular predictions.
Not Every Token Needs Forgetting: Selective Unlearning Balancing Forgetting and Utility in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Conventional unlearning approaches forget all tokens in a target document, including common tokens that carry general knowledge.
Approach: They propose a method that identifies a critical subset of tokens within the forgetting set that is relevant to the unwanted information and unlearns only those tokens.
Outcome: Experiments on two benchmarks and six baseline unlearning algorithms show that selective unlearning achieves effective unlearning on the targeted forget data.
Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulation (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated impressive performance, but they keep repeating similar mistakes due to their inability to capture relationships among samples.
Approach: They propose a tuning-free rule accumulation framework that guides LLMs in improving their performance by learning from previous mistakes.
Outcome: The proposed framework improves over baselines by a large margin over previous frameworks.
Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection (2026.findings-eacl)

Copied to clipboard

Challenge: Existing methods to improve robustness require changing the fine-tuning process or large-scale data augmentation, which are infeasible or cost prohibitive for closed-source models.
Approach: They propose to prioritize more complex examples or replace existing training examples with LLM-generated data to improve performance on OOD NLI datasets.
Outcome: The proposed methods improve performance on difficult OOD datasets while training with synthetic data leads to substantial improvements on easier OOD data.
Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions (2025.findings-naacl)

Copied to clipboard

Challenge: Large language models have demonstrated great performance across various benchmarks, but data contamination is a concern in their evaluation.
Approach: They analyze 50 papers on data contamination detection and test three of them as case studies to identify the possibility of data contamination.
Outcome: The proposed methods can detect membership inference attacks on instance-level data, and can perform similar to random guessing on LLM pretraining datasets.
CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing fine-tuning paradigms focus on aligning LLMs with task-specific objectives.
Approach: They propose a pipeline that leverages human priors to automatically generate token-level causal signals and introduce the Re-Attention mechanism to guide training.
Outcome: The proposed pipeline achieves an average improvement of 5.76% on the STG dataset and 1.56% on downstream tasks.

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