Challenge: Existing approaches to reasoning using transformers are limiting, resulting in inconsistent results in arithmetic and QA benchmarks.
Approach: They propose a novel approach that utilizes probabilistic logical rules as constraints in the fine-tuning phase without relying on them in the inference stage.
Outcome: The proposed approach improves the transformer-based language model’s intrinsic reasoning and makes their probabilistic logical reasoning process more explicit and explainable.

Similar Papers

Can Language Models Learn Embeddings of Propositional Logic Assertions? (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for automating reasoning can no longer be used for natural language tasks.
Approach: They propose to use transformer-based language models to reason about knowledge expressed in natural language rather than using LMs to perform reasoning directly.
Outcome: The proposed approach is feasible to some extent, but lacks robustness.
Logical Transformers: Infusing Logical Structures into Pre-Trained Language Models (2023.findings-acl)

Copied to clipboard

Challenge: Existing pre-trained language models that ignore the logical structures underlying natural language text often lack the ability to capture and encode key logical information in the input sequences.
Approach: They propose to construct logic-aware input embeddings for transformer language models through logic detection, logic mapping and hierarchical logical projections and then develop a new modeling paradigm that can upgrade existing transformer language model into logical transformers to boost their performance.
Outcome: The proposed model can achieve superior performance on four important and challenging tasks.
Identifying the limits of transformers when performing model-checking with natural language (2023.eacl-main)

Copied to clipboard

Challenge: Recent studies have focused on transformer models’ ability to perform reasoning on text, but the above question has not been adequately answered.
Approach: They investigated the problem of model-checking with natural language to determine whether transformers can comprehend logical semantics in natural language.
Outcome: The proposed model-checking problem is suited to address this issue but is untouched in natural language inference research.
Probabilistic Transformer: A Probabilistic Dependency Model for Contextual Word Representation (2023.findings-acl)

Copied to clipboard

Challenge: Syntactic structures were deemed essential in natural language processing . but since the deep learning revolution, NLP has been dominated by neural models that do not consider syntactical structures in their design.
Approach: They propose a model that models latent representations of words in a sentence . they use a conditional random field to model latent and dependency arcs .
Outcome: The proposed model performs competitively to transformers on small to medium sized datasets.
Can Transformers Reason in Fragments of Natural Language? (2022.emnlp-main)

Copied to clipboard

Challenge: Recent work on natural language inference has identified two strands of research .
Approach: They investigate whether neural networks have acquired logical principles from natural language . they use transformer-based models to detect valid inferences in controlled fragments of natural language.
Outcome: The proposed model overfits to superficial patterns in the data rather than acquiring the logical principles governing reasoning in natural language fragments.
RuleBERT: Teaching Soft Rules to Pre-Trained Language Models (2021.emnlp-main)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) are limited in their ability to capture and use common-sense knowledge.
Approach: They propose to teach PLMs how to reason with soft Horn rules by leveraging logical rules to learn how to predict precise probabilities.
Outcome: The proposed model performs well on logical rules that were unseen at training.
HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation (2023.acl-long)

Copied to clipboard

Challenge: Existing techniques to fine-tune pre-trained language models on downstream tasks are inadequate.
Approach: They propose a technique to perturb hidden Transformers representations by enhancing generalization of hidden representations from different layers.
Outcome: The proposed technique outperforms vanilla fine-tuning and enhances generalization of hidden representations from different layers.
Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis (2022.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) have gained increasing popularity due to compelling prediction performance in diverse natural language processing tasks.
Approach: They compare three popular options for encoding and Temp Scaling for PLMs . they recommend using Temp Loss as uncertainty quantifier and Focal Loss for fine-tuning .
Outcome: Using pre-trained language models, we compare three options on NLP classification tasks and domain shift.
FaiRR: Faithful and Robust Deductive Reasoning over Natural Language (2022.acl-long)

Copied to clipboard

Challenge: Currently, black-box models generate both the proof graph and intermediate inferences within the same model and thus may be unfaithful.
Approach: They propose a transformer-based model that can perform deductive reasoning on a logical rulebase containing rules and statements written in natural language.
Outcome: The proposed model is robust to language perturbations and faster at inference than previous models on existing reasoning datasets.
Transformer versus LSTM Language Models trained on Uncertain ASR Hypotheses in Limited Data Scenarios (2022.lrec-1)

Copied to clipboard

Challenge: Existing studies show that domain-specific LMs can only rely on limited in-domain speech data . a qualitative analysis reveals that Transformer LM can predict less frequent words .
Approach: They propose a method to train Transformer LMs on ASR confusion networks . they find they are better at exploiting alternate uncertain ASR hypotheses .
Outcome: The proposed method reduces perplexity by 3-6% on AMI scenarios but performs similar to LSTM LMs on Verbmobil conversational corpus.

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