Papers with GPT3.5
MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making (2024.emnlp-main)
Copied to clipboard
| Challenge: | Insight is a form of long-term memory for an agent but lack of general insight can undermine its effectiveness. |
| Approach: | They propose an embodied agent that summarises and utilizes insight effectively across different scales and generates task-specific and high-level insight, stores it in a database, and then uses relevant insight from it. |
| Outcome: | The proposed agent outperforms a similar agent when planning by GPT3.5 and is more robust when faced with domain-shifting scenarios. |
Language Models Hallucinate, but May Excel at Fact Verification (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have produced non-factual outputs . however, current LLMs suffer from the hallucination issue . |
| Approach: | They propose to use instruction-tuned LLMs to generate factual outputs . they find that FLAN-T5-11B performs best as a fact verifier . |
| Outcome: | The proposed method outperforms more capable LLMs like GPT3.5 and ChatGPT in the human evaluation. |
TigerLLM - A Family of Bangla Large Language Models (2025.acl-short)
Copied to clipboard
| Challenge: | linguistic disparity is particularly evident for Bangla, the 5th most spoken language . open-source Bangla LLMs have limited reproducibility and performance gaps . |
| Approach: | They propose a family of Bangla LLMs that outperform open-source alternatives and benchmarks and establish a new benchmark for future Bangla language modeling. |
| Outcome: | The proposed models outperform existing models and outperformed proprietary models across six benchmarks. |
LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on learning and enhancing large language models to understand and generate natural language. |
| Approach: | They propose a computational bionic memory mechanism equipped with a parameter-efficient fine-tuning schema to personalize medical assistants. |
| Outcome: | The proposed method can enhance the response with aware of previous mistakes for new queries during a dialogue session, but the training costs are prohibitive. |
Testing the Depth of ChatGPT’s Comprehension via Cross-Modal Tasks Based on ASCII-Art: GPT3.5’s Abilities in Regard to Recognizing and Generating ASCII-Art Are Not Totally Lacking (2024.findings-eacl)
Copied to clipboard
| Challenge: | In the months since its release, ChatGPT and its underlying model, GPT3.5, have garnered massive attention due to their potent mix of capability and accessibility. |
| Approach: | They examine GPT3.5's aptitude for visual tasks using ASCII-art without overt distillation into a lingual summary. |
| Outcome: | The proposed model performs well on image recognition and generation tasks. |
Generative Interpretation: Toward Human-Like Evaluation for Educational Question-Answer Pair Generation (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing evaluation methods often fail to produce objective results and favor high similarity to the ground-truth question-answer pairs. |
| Approach: | They propose an alternative approach to evaluate question-answer generation using Generative Interpretation (GI) GI outperforms existing evaluation methods in terms of human alignment . |
| Outcome: | The proposed approach outperforms existing evaluation methods in human alignment and shows comparable performance with GPT3.5, only with BART-large. |
Comparing the Evaluation and Production of Loophole Behavior in Humans and Large Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that loophole-seeking is frequent and intuitive in children . a large number of models capture the pragmatic understanding required for loopholes, says a researcher . |
| Approach: | a study compares large language models to humans to examine loophole behavior . they found that models struggle to recognize humor in creative exploitation of loopholes . |
| Outcome: | a study compares state-of-the-art models to humans to examine loophole behavior in humans . a large language model can generate loopholes, but only two are capable of generating them . |
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated excellent performance in numerous tasks but the parameterized knowledge stored within LLMs may be incomplete and hard to incorporate up-to-date knowledge. |
| Approach: | They propose a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model’s problem-solving capabilities. |
| Outcome: | The proposed method outperforms existing benchmarks on GPT3.5, Llama2 and other large language models significantly enhancing factual reasoning capabilities and reducing hallucinations. |
ViPE: Visualise Pretty-much Everything (2023.emnlp-main)
Copied to clipboard
| Challenge: | Figure and non-literal expressions are deeply integrated in human communication . text-to-image models like Stable Diffusion struggle to depict non-figural expression . |
| Approach: | They propose a series of lightweight and robust language models that can be used to visualise non-literal expressions. |
| Outcome: | The proposed language models are more robust than existing models and can generate high-quality images. |
ContraDoc: Understanding Self-Contradictions in Documents with Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Detecting contradictions in texts is often regarded as determining relation between hypothesis and piece of premise. |
| Approach: | They propose a human-annotated dataset to study self-contradictions in long documents . they analyze the capabilities of four open-source and commercially available LLMs . |
| Outcome: | The proposed dataset outperforms open-source LLMs on document-level tasks but struggles with self-contradictions that require more nuance and context. |
Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation (2024.acl-long)
Copied to clipboard
| Challenge: | Logic-based approaches to reasoning have lost popularity due to limited scalability and coverage. |
| Approach: | They present a dataset of 28K sentence-level NL-FOL pairs from GPT4 and a LogicLLaMA2-7B/13B fine-tuned on MALLS for NL translation. |
| Outcome: | The proposed model can be used standalone or to correct previously generated rules by GPT3.5. |
The student becomes the master: Outperforming GPT3 on Scientific Factual Error Correction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for Factual Claim Correction rely on a verification model to guide the correction process. |
| Approach: | They propose a claim correction system that does not require a verifier but outperforms existing methods by a considerable margin. |
| Outcome: | The proposed system outperforms existing methods by a considerable margin on the SciFact dataset, 77% on SciFACT-Open and 72.75% on the CovidFact data set. |
Tell Me What You Know About Sexism: Expert-LLM Interaction Strategies and Co-Created Definitions for Zero-Shot Sexism Detection (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) with chat interfaces are increasingly popular in various scientific fields, for a variety of tasks related to social science research questions. |
| Approach: | They propose to use large language models to combine human and machine expertise to improve their models' performance. |
| Outcome: | The proposed model performs better with co-created definitions than with expert-written definitions. |
LegalDiscourse: Interpreting When Laws Apply and To Whom (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in NLP and information retrieval have already enabled practical applications. |
| Approach: | They propose a 'discourse' taxonomy for span-and-relation parsing of legal texts . they use a dataset of 602 state-level law paragraphs with 3,715 discourse spans and 1,671 relations to investigate the increase in liquor licenses and decrease in applicable laws. |
| Outcome: | The proposed model performs poorly at span identification and relation classification, but lags far below human level. |
ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable in-context learning capabilities in various natural language processing tasks. |
| Approach: | They propose a novel approach ERA-CoT which aids LLMs in understanding context by capturing relationships between entities and supports the reasoning of diverse tasks through Chain-of-Thoughts (CoT). |
| Outcome: | The proposed method improves on GPT3.5 and previous SOTA prompting methods by an average of 5.1% compared to previous prompting approaches. |
Knowledge-based Consistency Testing of Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) are being increasingly utilized in real-world applications. |
| Approach: | They propose an automated testing framework which leverages a knowledge graph to construct test cases. |
| Outcome: | The proposed framework generates 19.2% error inducing inputs and reveals 16.5% knowledge gap across all tested LLMs. |
To Err Is Human, but Llamas Can Learn It Too (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Specifically, we fine-tune Llama 2 LMs for error generation and find that this approach yields synthetic errors akin to human errors. |
| Approach: | They propose to fine-tune Llama 2 LMs for error generation and train GEC Llma models using these artificial errors. |
| Outcome: | The proposed approach outperforms state-of-the-art models with gains ranging between 0.8 and 6 F0.5 points across all languages tested. |
Large Language Models are Few-Shot Training Example Generators: A Case Study in Fallacy Recognition (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing work on fallacy recognition is still in its early stages, with limited datasets available. |
| Approach: | They propose to use GPT3.5 to generate synthetic examples and explore prompt settings to improve the representation of the infrequent classes. |
| Outcome: | The proposed model improves on existing models and generates synthetic examples with GPT3.5. |
ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler (2024.lrec-main)
Copied to clipboard
| Challenge: | State-of-the-art intent classification and slot filling methods rely on data-intensive deep learning models . large language models exhibit remarkable zero-shot performance across various natural language tasks. |
| Approach: | They propose an approach framing IC and SF as language generation tasks for instruction-LLMs with a more efficient SF-prompting method. |
| Outcome: | The proposed approach outperforms state-of-the-art IC+SF method and in-context learning methods with GPT3.5 (175B). |
Token Prediction as Implicit Classification to Identify LLM-Generated Text (2023.emnlp-main)
Copied to clipboard
| Challenge: | a novel approach for identifying large language models (LLMs) involved in text generation is proposed . instead of adding an additional classification layer, we reframe the classification task as a next-token prediction task . |
| Approach: | They propose a novel approach for identifying large language models involved in text generation . instead of adding an additional classification layer, they reframe the task as a next-token prediction task . |
| Outcome: | The proposed method performs exceptionally well in the text classification task . it can distinguish distinctive writing styles among various LLMs even without an explicit classifier. |
Global Eye: Breaking the “Fixed Thinking Pattern” during the Instruction Expansion Process (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods focus on constructing multi-perspective prompts to expand instructions, overlooking the “Fixed Thinking Pattern” issue of Large Language Models. |
| Approach: | They propose a method that analyzes the statistical characteristics of newly generated instructions and updates the prompts after a fixed number of instruction expansions. |
| Outcome: | The proposed method surpasses open-source LLMs and GPT3.5 in several metrics. |
CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to zero-shot commonsense question answering use incomplete CSKBs . lack of human annotations makes sampled negative examples potentially uninformative and contradictory. |
| Approach: | They propose a framework that abstracts a commonsense knowledge triple to many higher-level instances, which increases the coverage of the CSKB and expands the ground-truth answer space. |
| Outcome: | Experiments show that CAR can generalize to zero-shot commonsense scenarios . lack of human annotations makes sampled negative examples potentially uninformative and contradictory. |
LocalTweets to LocalHealth: A Mental Health Surveillance Framework Based on Twitter Data (2024.lrec-main)
Copied to clipboard
| Challenge: | Prior research on Twitter has provided positive evidence of its utility in developing supplementary health surveillance systems. |
| Approach: | They propose a framework to surveil public health, focusing on mental health outcomes by using tweets from 765 neighborhoods in the USA. |
| Outcome: | The proposed framework achieves the highest F1-score and accuracy over the previous framework, and extrapolates CDC’s estimates to proxy unreported neighborhoods. |
Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent benchmarks have assessed language models' numerical abilities . limitations include tokenization and representation of numbers in text, hallucination, and a lack of numerical commonsense knowledge. |
| Approach: | They propose a hierarchical taxonomy for numerical reasoning skills that includes representation, number sense, manipulation, and complex reasoning. |
| Outcome: | The proposed model outperforms other models on the tabular Natural Language Inference task. |
Only a Little to the Left: A Theory-grounded Measure of Political Bias in Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Political biases in language models can affect performance in many applications . political biased models are often left-leaning, but are generally more left- leaning for instruction-tuned models . |
| Approach: | They propose to use the Political Compass Test to measure political bias in language models . they use survey-based evaluation tools to test prompts and classify their political stances . |
| Outcome: | The proposed model is based on the Political Compass Test, but is not scientifically valid. |
Zero-Shot Spoken Language Understanding via Large Language Models: A Preliminary Study (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have shown promising results in zero-shot settings, which motivates us to explore prompt-based methods. |
| Approach: | They propose a two-stage framework which transforms the SLU task into a question-answering problem by directly prompting LLMs. |
| Outcome: | The proposed framework can be built by directly prompting LLMs to understand user needs without training data. |