Parametric Knowledge is Not All You Need: Toward Honest Large Language Models via Retrieval of Pretraining Data (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models are highly capable of answering questions, but they are often unaware of their own knowledge boundary, i.e., knowing what they know and what they don’t know. |
| Approach: | They propose a method to evaluate LLM honesty using Pythia with publicly available pretraining data. |
| Outcome: | The proposed method is based on Pythia, a truly open LLM with publicly available pretraining data. |
Similar Papers
PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning (2026.findings-acl)
Copied to clipboard
Langming Liu, Kangtao Lv, Haibin Chen, Weidong Zhang, Yejing Wang, Shilei Liu, Xin Tong, Yujin Yuan, Yongwei Wang, Wenbo Su, Bo Zheng
| Challenge: | Large language models suffer from factual hallucinations where they generate verifiable falsehoods. |
| Approach: | They propose a framework that integrates reinforcement learning into the pretraining phase to consolidate factual knowledge. |
| Outcome: | The proposed framework significantly alleviates factual hallucinations and outperforms state-of-the-art methods. |
Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for unlearning in large language models often hallucinate, generate abnormal token sequences, or behave inconsistently, raising safety and trust concerns. |
| Approach: | They propose a formal definition of unlearning honesty that preserves both utility and honesty on retained knowledge and ensures effective forgetting while encouraging the model to acknowledge its limitations. |
| Outcome: | The proposed method achieves highest rejection rate and refusal stability on Q A tasks from the forget set, nearly double the second-best method. |
How Much Knowledge Can You Pack Into the Parameters of a Language Model? (2020.emnlp-main)
Copied to clipboard
| Challenge: | In this paper, we show that large neural language models trained on unstructured text can attain competitive results on open-domain question answering benchmarks without access to external knowledge. |
| Approach: | They propose to fine-tune pre-trained neural language models to answer questions without external knowledge . they show that this approach scales with model size and performs competitively . |
| Outcome: | The proposed approach scales with model size and performs competitively with open-domain systems that explicitly retrieve answers from an external knowledge source when answering questions. |
Machine Unlearning of Pre-trained Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Using curated datasets, we establish a robust benchmark for unlearning performance, demonstrating that these methods are over 105 times more computationally efficient than retraining. |
| Approach: | They propose a framework for machine unlearning in pre-trained LLMs and integrate gradient ascent with gradient descent on in-distribution data to achieve robustness. |
| Outcome: | The proposed framework is over 105 times more efficient than retraining on in-distribution data and provides detailed guidelines for efficient hyperparameter tuning in the unlearning process. |
DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text (2024.findings-naacl)
Copied to clipboard
| Challenge: | Retrievalaugmented LLMs have been used to ground LLM in external knowledge . a gap exists in the current landscape regarding the effectiveness of grounding LLM on heterogeneous knowledge sources. |
| Approach: | They propose a model that uses symbolic language to generate symbolic queries . they use a dataset that is generated using predefined reasoning chains and human annotation . |
| Outcome: | The proposed model outperforms previous approaches by a significant margin in QA tasks over text. |
Estimating Knowledge in Large Language Models Without Generating a Single Token (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to evaluate knowledge in large language models require querying and evaluating the model's generated responses. |
| Approach: | They ask whether it is possible to estimate how knowledgeable a model is about a subject entity only from its internal computation. |
| Outcome: | The proposed model performs well with QA accuracy and FActScore . it can be leveraged to guide decisions on how to apply further training or augment queries with retrieval. |
SKILL: Structured Knowledge Infusion for Large Language Models (2022.naacl-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks. |
| Approach: | They propose a method to infuse structured knowledge into large language models by directly training T5 models on factual triples of knowledge graphs (KGs). |
| Outcome: | The proposed method outperforms baseline models on FreebaseQA and WikiHop, as well as the Wikidata-answerable subset of TriviaQA and NaturalQuestions. |
Do Neural Language Models Overcome Reporting Bias? (2020.coling-main)
Copied to clipboard
| Challenge: | Recent studies show that pre-trained language models can overcome reporting bias by estimating the plausibility of rare but unspoken facts. |
| Approach: | They revisit the experiments conducted by Gordon and Van Durme (2013) . they find that pre-trained language models overestimate the very rare . |
| Outcome: | The proposed approach overestimates the rare at the expense of the rare, while minimizing reporting bias. |
Robust and Scalable Model Editing for Large Language Models (2024.lrec-main)
Copied to clipboard
Yingfa Chen, Zhengyan Zhang, Xu Han, Chaojun Xiao, Zhiyuan Liu, Chen Chen, Kuai Li, Tao Yang, Maosong Sun
| Challenge: | Existing methods that ignore contextual knowledge fail to reliably fall back to parametric knowledge when presented with irrelevant context. |
| Approach: | They propose to use contextual knowledge to update and correct LLMs' knowledge by in-context editing instead of retraining. |
| Outcome: | The proposed method outperforms current state-of-the-art methods by a large margin on a dataset that contains irrelevant questions. |
ULMR: Unlearning Large Language Models via Negative Response and Model Parameter Average (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) have attracted significant interest from the research community due to their broad applicability in many language-oriented tasks. |
| Approach: | They propose a framework which uses pre-training datasets to rewrite instructions and generate negative responses to preserve the performance of the original LLM. |
| Outcome: | The proposed framework can erase the pre-training data while maintaining the performance of the original model. |