Manipulating the Difficulty of C-Tests (P19-1)

Copied to clipboard

Challenge: a new manipulation strategy for increasing and decreasing difficulty of C-tests is proposed for language learning . we use two strategies to generate C- tests with the desired difficulty level . learning languages is of utmost importance in an international society .
Approach: They propose two manipulation strategies for increasing and decreasing difficulty of C-tests automatically.
Outcome: The proposed manipulation strategies increase and decrease difficulty of C-tests automatically.

Similar Papers

Revisiting Generalization Across Difficulty Levels: It’s Not So Easy (2026.eacl-long)

Copied to clipboard

Challenge: Existing research is mixed regarding whether training on easier or harder data leads to better results.
Approach: They examine how well large language models generalize across different task difficulties by using a large dataset and a well-established difficulty metric.
Outcome: The results show that training on hard data can't achieve consistent improvements across the full range of difficulties.
The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for difficulty estimation rely on repeated response sampling, auxiliary models, or fine-tuning the target model itself.
Approach: They propose a method that leverages only the hidden representations produced by large language models.
Outcome: The proposed method outperforms baselines in difficulty estimation on textual and multimodal tasks and improves adaptive reasoning strategies with fewer generated tokens.
Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation (2026.findings-eacl)

Copied to clipboard

Challenge: Practicing conversations with large language models is a promising alternative to traditional in-person language learning.
Approach: They propose a new token-level evaluation metric, Token Miss Rate, that measures the proportion of incomprehensible tokens per utterance and correlates strongly with human judgments.
Outcome: The proposed methods improve comprehensibility for beginner speakers from 39.4% to 83.3%, compared with prompting alone and a token-level evaluation metric, Token Miss Rate (TMR).
Do you have the right scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods (2020.acl-main)

Copied to clipboard

Challenge: Pre-trained language models can be fine-tuned on task-specific datasets, but fine-timing can lead to over- and/or under-estimation problems.
Approach: They propose a method to transfer probability mass from over-estimated regions to under-estimates by truncating and transferring probability mass between over- and under-estimating regions.
Outcome: The proposed method outperforms the fine-tuning approach on a variety of datasets.
Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting (2021.acl-long)

Copied to clipboard

Challenge: Existing QG systems perform substantially worse in answering multi-hop questions than single-hop ones.
Approach: They propose a framework that progressively increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain.
Outcome: The proposed framework increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain.
CrossQG: Improving Difficulty-Controllable Question Generation through Consistency Enhancement (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models can generate questions with controlled difficulty, but they often fail to align with the given target difficulty.
Approach: They propose a question generation method that requires no tuning of generator parameters yet significantly improves difficulty consistency.
Outcome: The proposed method outperforms several mainstream methods on high-quality question answering datasets and achieves superior consistency with target difficulty.
Editing Large Language Models: Problems, Methods, and Opportunities (2023.emnlp-main)

Copied to clipboard

Challenge: Recent advances in model editing for LLMs have created challenges and opportunities for the community.
Approach: They propose to alter the behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs.
Outcome: The proposed method alters behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs.
Is It Possible to Modify Text to a Target Readability Level? An Initial Investigation Using Zero-Shot Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Text simplification and elaboration tasks are limited to only relatively altering the readability of texts to cater to a diverse audience.
Approach: They propose to generate 8 versions of a text at different readability levels using ChatGPT and Llama-2 and introduce a two-step process to generate paraphrases.
Outcome: The proposed task requires the generation of 8 versions at various target readability levels for each input text.
Machine Learning–Driven Language Assessment (2020.tacl-1)

Copied to clipboard

Challenge: Language proficiency tests are cumbersome to create and maintain, and items may be copied and leaked or simply used too often.
Approach: They propose a method that uses machine learning and natural language processing to induce proficiency scales and linguistic models to estimate item difficulty directly for computer-adaptive testing.
Outcome: The proposed method produces scores that are reliable and reliable while generating item banks large enough to satisfy security requirements.
Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) require vast datasets for pretraining, making it difficult to train LLMs from scratch for lowresource languages.
Approach: They propose to transform a language of the GLUE benchmark and then fine tune a pretrained model on that dataset.
Outcome: The proposed models recover from syntactic-style shifts, but cannot recover from vocabulary misalignment and embedding matrix re-initialization, even with continued pretraining on 15 million tokens.

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