Challenge: Training language models and examining their linguistic behaviors is a common protocol in computational linguistics for studying linguistic phenomena and modeling human language processing.
Approach: They replicate three prior studies with hyperparameters varied within a practical range and show that modest hyperparametric changes can alter qualitative conclusions about models’ linguistic abilities.
Outcome: The results show that hyperparameter changes can alter qualitative conclusions and reverse the ranking of models.

Similar Papers

Exploring the Sensitivity of LLMs’ Decision-Making Capabilities: Insights from Prompt Variations and Hyperparameters (2023.findings-emnlp)

Copied to clipboard

Challenge: Prior studies have compared the decision-making abilities of large language models with those of humans from a psychological perspective.
Approach: They examine LLMs' performance on the Horizon decision-making task studied by Binz and Schulz (2023) they observe that the decision- making abilities fluctuate based on input prompts and temperature settings.
Outcome: The results show that LLMs display a human-like exploration–exploitation tradeoff after simple adjustments to the prompt.
The Sensitivity of Language Models and Humans to Winograd Schema Perturbations (2020.acl-main)

Copied to clipboard

Challenge: Large-scale pre-trained language models are driving recent improvements in perfromance on the Winograd Schema Challenge . a diagnostic dataset shows that these models are sensitive to linguistic perturbations that minimally affect human understanding .
Approach: They propose to use a dataset to test pre-trained language models for the Winograd Schema Challenge . they show that these models are sensitive to linguistic perturbations that minimally affect human understanding .
Outcome: The proposed models are sensitive to linguistic perturbations that minimally affect human understanding.
Uncovering Constraint-Based Behavior in Neural Models via Targeted Fine-Tuning (2021.acl-long)

Copied to clipboard

Challenge: Existing work has shown that non-linguistic biases in language models obscure linguistic knowledge.
Approach: They hypothesize competing linguistic processes within a language could obscure linguistic knowledge.
Outcome: The proposed model can learn linguistic constraints in a language and their relative ranking, the authors show . linguistic biases can obscure underlying linguistic knowledge, they show a single phenomenon in four languages.
Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation (2025.coling-main)

Copied to clipboard

Challenge: Generative large language models generate a high-dimensional probability distribution over all tokens in their vocabulary.
Approach: They conduct extensive sensitivity analyses to determine how hyperparameter choices shape the outputs of generative large language models.
Outcome: The proposed methods influence the distribution of diversity and coherence metrics in human-written text, but the optimal configurations vary across models and tasks.
Cognitive Effects and Biases in Large Language Models (2026.eacl-tutorials)

Copied to clipboard

Challenge: This tutorial bridges psychology and NLP to clarify cognitive effects and biases in large language models.
Approach: This tutorial bridges psychology and NLP to clarify cognitive effects and biases in large language models.
Outcome: This tutorial bridges psychology and NLP to clarify cognitive effects and biases in large language models.
Predicting Reference: What do Language Models Learn about Discourse Models? (2020.emnlp-main)

Copied to clipboard

Challenge: a growing literature that probes neural language models to assess their latent acquisition of grammatical knowledge has not investigated their acquisition of discourse modeling ability.
Approach: They draw on a psycholinguistic literature that has established how different contexts affect referential biases concerning who is likely to be referred to next.
Outcome: The proposed models do not resemble human language users, the authors show . their models capture the linguistic knowledge required to perform discourse modeling .
Overestimation of Syntactic Representation in Neural Language Models (2020.acl-main)

Copied to clipboard

Challenge: Several testing methodologies have been developed to probe models’ syntactic representations.
Approach: They propose a method to determine syntactic structure by training a model on strings generated according to a template and testing its ability to distinguish between similar ones with different syntax.
Outcome: The proposed method reproduces positive results with two non-syntactic baseline language models: an n-gram model and an LSTM model trained on scrambled inputs.
A Thorough Examination of Decoding Methods in the Era of LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Decoding methods are essential for converting language models from next-token predictors into practical task solvers.
Approach: They propose to evaluate decoding methods in general-purpose large language models . they find that decoding method performance is notably task-dependent .
Outcome: The proposed methods perform task-dependently and are influenced by alignment, model size, and quantization.
The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text (2024.findings-naacl)

Copied to clipboard

Challenge: a new study examines the effects of training language models on synthetic data generated by their predecessors.
Approach: They propose to use recursive finetuning techniques to assess linguistic diversity of models.
Outcome: The proposed metrics show a decrease in diversity of model outputs through successive iterations, especially for tasks demanding high levels of creativity.
Unveiling the Generalization Power of Fine-Tuned Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, but the comprehensive effects of fine-tuning on the LLMs’ generalization ability are not fully understood.
Approach: They conduct extensive experiments across five distinct language tasks on different datasets to investigate whether fine-tuning affects the generalization ability intrinsic to LLMs.
Outcome: The proposed model can generalize to different domains and tasks by integrating the in-context learning strategy during fine-tuning on generation 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