Papers with probing analysis
Artificial Text Detection via Examining the Topology of Attention Maps (2021.emnlp-main)
Copied to clipboard
Laida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev
| Challenge: | Existing methods for text detection lack interpretability and robustness towards unseen models. |
| Approach: | They propose three new types of interpretable topological features based on topological data analysis which is currently understudied in the field of NLP. |
| Outcome: | The proposed features outperform count- and neural-based baselines up to 10% on three common datasets and tend to be the most robust towards unseen GPT-style generation models. |
Exploring the Effects of Negation and Grammatical Tense on Bias Probes (2022.aacl-short)
Copied to clipboard
| Challenge: | Existing studies on negation in language models have shown that it does not affect correlations between gendered-pronouns and occupations. |
| Approach: | They propose to add negation to bias probes to alter the grammatical tense of verbs in bias probe and to aggregate results across tenses to better represent existing correlations. |
| Outcome: | The proposed method does not alter correlations between gendered-pronouns and occupations, but altering the grammatical tense of verbs does. |
Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods, such as a n-terminal coding, do not provide accurate data for large language models. |
| Approach: | They propose a lightweight framework that leverages attention distributions and uncertainty signals in a single-pass decoding. |
| Outcome: | Experiments on open-book QA datasets show that DAGCD improves faithfulness and robustness while preserving computational efficiency. |
Less Mature is More Adaptable for Sentence-level Language Modeling (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies fine-tune encoders or contrastive learning approaches to learn sentence representations. |
| Approach: | They propose to use sentence-level models to study how sentence representations influence downstream task performance. |
| Outcome: | The proposed models outperform token-level models in terms of time and data efficiency. |
Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study (2025.findings-emnlp)
Copied to clipboard
Yujun Zhou, Jiayi Ye, Zipeng Ling, Yufei Han, Yue Huang, Haomin Zhuang, Zhenwen Liang, Kehan Guo, Taicheng Guo, Xiangqi Wang, Xiangliang Zhang
| Challenge: | Existing benchmarks that rely on final-answer accuracy fail to capture the quality of the reasoning process. |
| Approach: | They propose a fine-grained evaluation framework that assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing. |
| Outcome: | The proposed framework assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing. |