Challenge: Autoregressive neural language models (LMs) generate a probability distribution over tokens at each time step given a prompt.
Approach: They propose to find a prompt that induces LMs to output a distribution as close as possible to the target, using either soft or hard gradient-based prompt tuning.
Outcome: The proposed model is able to generate a distribution as close as possible to a target given a prompt, and it can be used to approximate distributions with low or high entropy.

Similar Papers

Demystifying optimized prompts in language models (2025.emnlp-main)

Copied to clipboard

Challenge: Modern language models (LMs) are not robust to out-of-distribution inputs.
Approach: They investigate the composition of machine generated (“optimized”) prompts and the mechanisms by which LMs parse and build predictions from them.
Outcome: The proposed prompts are primarily composed of punctuation and noun tokens, which are more rare in the training data.
How to Compute the Probability of a Word (2024.emnlp-main)

Copied to clipboard

Challenge: Language models estimate a probability distribution over strings in a natural language . many recent linguistic studies have been incorrectly computing word probabilities .
Approach: They propose to use the correct method to compute word probabilities . they highlight issues when relying on models that use end-of-word tokenisers .
Outcome: Empirically, correcting the widespread bug affects measured outcomes in sentences and lexical optimisation analyses.
How Do Neural Sequence Models Generalize? Local and Global Cues for Out-of-Distribution Prediction (2021.emnlp-main)

Copied to clipboard

Challenge: Using RNN and transformer language models, we show consistent generalization in out-of-distribution contexts.
Approach: They propose two idealized models of generalization in next-word prediction . they show that neural language models interpolate between these two forms of generalisation .
Outcome: The proposed models exhibit consistent generalization in out-of-distribution contexts.
How Can We Know What Language Models Know? (2020.tacl-1)

Copied to clipboard

Challenge: Recent work examines knowledge contained in language models by having the LM fill in the blanks of prompts such as “Obama is a __ by profession”.
Approach: They propose mining-based and paraphrasing-based methods to automatically generate high-quality and diverse prompts, as well as ensemble methods to combine answers from different prompts.
Outcome: The proposed methods improve accuracy from 31.1% to 39.6% on the LAMA benchmark for extracting relational knowledge from LMs.
Unnatural language processing: How do language models handle machine-generated prompts? (2023.findings-emnlp)

Copied to clipboard

Challenge: Language model prompt optimization research has shown that semantically and grammatically well-formed manually crafted prompts are outperformed by automatically generated token sequences with no apparent meaning or syntactic structure.
Approach: They propose to use machine-generated prompts to probe how models respond to input that is not composed of natural language expressions.
Outcome: The proposed model outperforms human-crafted prompts on a target zero-shot task.
Prompt Compression for Large Language Models: A Survey (2025.naacl-long)

Copied to clipboard

Challenge: Current methods for improving LLM efficiency focus on optimizing the model itself, while prompt-centric methods focus on lowering the complexity of input.
Approach: They propose to use prompt compression to optimize the compression encoder and combine hard and soft prompt methods to improve the efficiency of LLMs.
Outcome: The proposed methods are categorized into hard prompt methods and soft prompt methods.
Reliability of Distribution Predictions by LLMs: Insights from Counterintuitive Pseudo-Distributions (2025.naacl-srw)

Copied to clipboard

Challenge: Recent studies highlight the use of Large Language Models (LLMs) for predicting response distributions as a cost-effective survey method.
Approach: They examine whether LLMs can rationally estimate distributions when presented with explanations that are against commonsense.
Outcome: The proposed models can rationally estimate distributions when presented with explanations that are against commonsense, but smaller or less human-optimized models follow explanations uncritically, compared to larger models that resist counterintuitive explanations by leveraging their pretraining-acquired knowledge.
Challenging the Explanation Based on Preceding Tokens: Discovering Transferable Non-Literal Biasing (2026.acl-short)

Copied to clipboard

Challenge: et al. (2017) show that the generated preceding tokens may push the large language model towards the target answer.
Approach: They find that generated preceding tokens may push large language models towards the target answer . they suggest that the LLM may intentionally use the semantically unrelated tokens to help generation of the target .
Outcome: The generated preceding tokens may push the large language model towards the target answer . the biased connotations of the target response can also transfer to other prompts .
Prompting is not a substitute for probability measurements in large language models (2023.emnlp-main)

Copied to clipboard

Challenge: Prompting is a dominant method for evaluating the linguistic knowledge of large language models (LLMs).
Approach: They compare metalinguistic prompting and direct probability measurements as ways of measuring LLMs’ linguistic knowledge.
Outcome: The results show that the results relying on metalinguistic prompts cannot be taken as conclusive evidence that an LLM lacks a particular linguistic generalization.
Understanding the Prompt Sensitivity (2026.acl-long)

Copied to clipboard

Challenge: Prompt sensitivity is a measure of how strongly the output of a large language model (LLM) depends on the exact wording of its input prompt.
Approach: They consider LLMs as multivariate functions and perform a first-order Taylor expansion to analyze the relationship between meaning-preserving prompts, their gradients, and log probabilities of the model’s next token.
Outcome: The proposed model disperses meaning-preserving inputs, making it difficult to reduce to 0. The proposed models also dispersing prompt variants are more likely to introduce prompt sensitivity risks in LLMs.

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