Papers with mean accuracy
Generating Effective CoT Traces for Mitigating Causal Hallucination (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models suffer from severe causal hallucination in event causality identification (ECI) there is currently no metric for quantifying causal hallucinonation for small models . |
| Approach: | They propose to fine-tune large language models with Chain-of-Thought (CoT) traces to mitigate hallucination in smaller models by introducing a new metric, the Causal Hallucinations Rate, which quantifies hallucinosity. |
| Outcome: | The proposed pipeline reduces causal hallucination in smaller models and improves mean accuracy under intentionally misleading intervention prompts. |
As easy as PIE: understanding when pruning causes language models to disagree (2025.findings-naacl)
Copied to clipboard
| Challenge: | Language Model pruning reduces the model's efficiency by removing weights, nodes, or other parts of its architecture. |
| Approach: | They propose to prune Language Models (LMs) to produce smaller, hence more efficient models with small loss to their effectiveness. |
| Outcome: | The proposed pruning method hurts data points that matter the most when pruning . the proposed pruning technique is based on a new study of NLP datasets . |
LCHAIM - Investigating Long Context Reasoning in Hebrew (2025.findings-acl)
Copied to clipboard
| Challenge: | a dataset designed to evaluate long premises and complex reasoning models in Hebrew is being used in research. |
| Approach: | They introduce a dataset to evaluate Hebrew NLI models on long premises and complex reasoning tasks. |
| Outcome: | The proposed dataset evaluates models on tasks involving long premises and complex reasoning. |
Compartmentalised Agentic Reasoning for Clinical NLI (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models produce fluent judgments for clinical natural language inference, yet fail when the decision requires the correct inferential schema rather than surface matching. |
| Approach: | They propose a compartmentalised agentic framework that routes each premise–statement pair to a reasoning family and applies a specialised solver with explicit verification and targeted refinement. |
| Outcome: | The proposed framework improves mean accuracy from 23% with direct prompting to 57%, with the largest gains on structurally demanding reasoning types. |
MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper (2025.emnlp-main)
Copied to clipboard
Runjia Zeng, Guangyan Sun, Qifan Wang, Tong Geng, Sohail Dianat, Xiaotian Han, Raghuveer Rao, Xueling Zhang, Cheng Han, Lifu Huang, Dongfang Liu
| Challenge: | Empirical evaluations show that Mixture of Expert Prompt Tuning outperforms state-of-the-art parameter efficient baselines on SuperGLUE. |
| Approach: | They propose a pretrain-then-fine-tune paradigm for manifold mapping using multiple prompt experts. |
| Outcome: | Empirical results show that the proposed approach outperforms state-of-the-art methods on SuperGLUE while reducing activated prompts by 79.25%. |
PaReNT (Parent Retrieval Neural Tool): A Deep Dive into Word Formation across Languages (2024.lrec-main)
Copied to clipboard
| Challenge: | a significant portion of words in a language share one or more roots with other existing lexemes as a result of word-formation processes. |
| Approach: | They present a deep-learning-based multilingual tool that performs retrieval and word formation classification in seven languages. |
| Outcome: | The proposed tool performs retrieval and word formation classification in English, German, Dutch, Spanish, French, Russian, and Czech. |