Thailand

Large Language Model (LLM) services and models often come with legal rules on *who* can use them and *how* they must use them. Assessing the compliance of the released LLMs is crucial, as these rules protect the interests of the LLM contributor and prevent misuse. In this context, we describe the novel fingerprinting problem of Black-box Identity Verification (BBIV). The goal is to determine whether a third-party application uses a certain LLM through its chat function. We propose a method called Targeted Random Adversarial Prompt (TRAP) that identifies the specific LLM in use. We repurpose adversarial suffixes, originally proposed for jailbreaking, to get a pre-defined answer from the target LLM, while other models give random answers. TRAP detects the target LLMs with over 95% true positive rate at under 0.2% false positive rate even after a single interaction. TRAP remains effective even if the LLM has minor changes that do not significantly alter the original function.

ACL 2024

TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification

compliance

model identification

large language model

fingerprinting

adversarial examples

poster

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

Stochastic sampling strategies such as top-k and top-p have been widely used in dialogue generation task. However, as an open-domain chatting system, there will be two different conversation scenarios, i.e. chit-chat and knowledge-based question answering. In the former situation, responses diversity is essential due to the one-to-many nature in dialogue. The latter, on the other hand, requires less randomness given that stochastic decoding strategy entails the risk of generating incorrect information. As a result, an adaptive and flexible decoding strategy is needed to cope with these two scenarios simultaneously. To this end, we propose the dynamic decoding strategy (DDS), which can adjust the decoding space w.r.t. different contexts. In DDS, both sequence-level and token-level adaptive search can be achieved to adjust the decoding process in a unified framework. Besides, our adaptive algorithm can not only be used during model inference, but it can also be applied during the model training stage to further enhance the performance. Comprehensive experiments indicate that the proposed decoding strategy can consistently improve the performance of pre-trained dialogue models when coupled with four well-used stochastic decoding algorithms.

Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation

Neural machine translation (NMT) systems often produce inadequate translations for named entities. In this study, we conducted preliminary experiments to examine the factors affecting the translation accuracy of named entities, specifically focusing on their translation difficulty and context diversity. Based on our observations, we propose a novel data augmentation strategy to enhance the accuracy of named entity translation. The main concept behind our approach is to increase both the context diversity and translation probability for the targeted named entity pair. To achieve this, we construct additional samples for named entities that exhibit high translation difficulty or low context diversity and use the augmented training data to re-train the final translation model. Furthermore, we propose an entity-aware machine translation metric that prefers the translation output to generate more accurate named entities. Our experimental results demonstrate significant improvements over the baseline in terms of general translation performance and named entity translation accuracy across various test sets, such as WMT news translation and terminology test sets.

Addressing Entity Translation Problem via Translation Difficulty and Context Diversity

For dialogue systems, the utilization of multimodal dialogue responses, as opposed to relying solely on text-only responses, offers the capability to describe different concepts through various modalities. This enhances the effectiveness of communication and elevates the overall conversational experience. However, current methods for dialogue-to-image retrieval are constrained by the capabilities of the pre-trained vision language models (VLMs). They struggle to accurately extract key information from conversations and are unable to handle long-turn conversations. In this paper, we leverage the reasoning capabilities of large language models (LLMs) to predict the potential features that may be present in the images to be shared, based on the dialogue context. This approach allows us to obtain succinct and precise descriptors, thereby improving the performance of text-image retrieval. Experimental results shows that our method outperforms previous approaches significantly in terms of Recall@k.

Visualizing Dialogues: Enhancing Image Selection through Dialogue Understanding with Large Language Models

Automatic methods for generating and gathering linguistic data have proven effective for fine-tuning Language Models (LMs) in languages less resourced than English. Still, while there has been emphasis on data quantity, less attention has been given to its quality. In this work, we investigate the impact of human intervention on machine-generated data when fine-tuning dialogical models. In particular, we study (1) whether post-edited dialogues exhibit higher perceived quality compared to the originals that were automatically generated; (2) whether fine-tuning with post-edited dialogues results in noticeable differences in the generated outputs; and (3) whether post-edited dialogues influence the outcomes when considering the parameter size of the LMs. To this end we created HED-IT, a large-scale dataset where machine-generated dialogues are paired with the version post-edited by humans. Using both the edited and unedited portions of HED-IT, we fine-tuned three different sizes of an LM. Results from both human and automatic evaluation show that the different quality of training data is clearly perceived and it has an impact also on the models trained on such data. Additionally, our findings indicate that larger models are less sensitive to data quality, whereas this has a crucial impact on smaller models. These results enhance our comprehension of the impact of human intervention on training data in the development of high-quality LMs.

Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models

Recent statements about the impressive capabilities of large language models (LLMs) are usually supported by evaluating on open-access benchmarks. Considering the vast size and wide-ranging sources of LLMs' training data, it could explicitly or implicitly include test data, leading to LLMs being more susceptible to data contamination. However, due to the opacity of training data, the black-box access of models, and the rapid growth of synthetic training data, detecting and mitigating data contamination for LLMs faces significant challenges. In this paper, we propose CDD, which stands for Contamination Detection via output Distribution for LLMs. CDD necessitates only the sampled texts to detect data contamination, by identifying the peakedness of LLM's output distribution. To mitigate the impact of data contamination in evaluation, we also present TED: Trustworthy Evaluation via output Distribution, based on the correction of LLM's output distribution. To facilitate this study, we introduce two benchmarks, i.e., DETCON and COMIEVAL, for data contamination detection and contamination mitigation evaluation tasks. Extensive experimental results show that CDD achieves the average relative improvements of 21.8%-30.2% over other contamination detection approaches in terms of Accuracy, F1 Score, and AUC metrics, and can effectively detect implicit contamination. TED substantially mitigates performance improvements up to 66.9\% attributed to data contamination across various contamination setups. In real-world applications, we reveal that ChatGPT exhibits a high potential to suffer from data contamination on HumanEval benchmark.

Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models

Current knowledge editing approaches struggle to effectively propagate updates to interconnected facts.
In this work, we delve into the barriers that hinder the appropriate propagation of updated knowledge within these models for accurate reasoning. To support our analysis, we introduce a novel reasoning-based benchmark, ReCoE (Reasoning-based Counterfactual Editing dataset), which covers six common reasoning schemes in the real world. We conduct an extensive analysis of existing knowledge editing techniques, including input-augmentation, finetuning, and locate-and-edit methods. We found that all model editing methods exhibit notably low performance on this dataset, especially within certain reasoning schemes. Our analysis of the chain-of-thought responses from edited models indicate that, while the models effectively update individual facts, they struggle to recall these facts in reasoning tasks. Moreover, locate-and-edit methods severely deteriorate the models' language modeling capabilities, leading to poor perplexity and logical coherence in their outputs.

Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks

This study explores the sycophantic tendencies of Large Language Models (LLMs), where these models tend to provide answers that match what users want to hear, even if they are not entirely correct. The motivation behind this exploration stems from the common behavior observed in individuals searching the internet for facts with partial or misleading knowledge. Similar to using web search engines, users may recall fragments of misleading keywords and submit them to an LLM, hoping for a comprehensive response. Our empirical analysis of several LLMs shows the potential danger of these models amplifying misinformation when presented with misleading keywords. Additionally, we thoroughly assess four existing hallucination mitigation strategies to reduce LLMs sycophantic behavior. Our experiments demonstrate the effectiveness of these strategies for generating factually correct statements. Furthermore, our analyses delve into knowledge-probing experiments on factual keywords and different categories of sycophancy mitigation.

Chaos with Keywords: Exposing Large Language Models Sycophancy to Misleading Keywords and Evaluating Defense Strategies

There currently exists a multitude of pre-trained transformer language models (LMs) that are readily available. From a practical perspective, this raises the question of which pre-trained LM will perform best if fine-tuned for a specific downstream NLP task. However, exhaustively fine-tuning all available LMs to determine the best-fitting model is computationally infeasible. 
To address this problem, we present an approach that inexpensively estimates a ranking of the expected performance of a given set of candidate LMs for a given task. Following a layer-wise representation analysis, we extend existing approaches such as H-score and LogME by aggregating representations across all layers of the transformer model. 
We present an extensive analysis of 20 transformer LMs, 6 downstream NLP tasks, and various estimators (linear probing, kNN, H-score, and LogME). Our evaluation finds that averaging the layer representations significantly improves the Pearson correlation coefficient between the true model ranks and the estimate, increasing from 0.58 to 0.86 for LogME and from 0.65 to 0.88 for H-score.

Choose Your Transformer: Improved Transferability Estimation of Transformer Models on Classification Tasks

Large language models (LLMs) adapted to follow user instructions are now widely deployed as conversational agents. In this work, we examine one increasingly common instruction-following task: providing writing assistance to compose a long-form answer. To evaluate the capabilities of current LLMs on this task, we construct KIWI, a dataset of knowledge-intensive writing instructions in the scientific domain. Given a research question, an initial model-generated answer and a set of relevant papers, an expert annotator iteratively issues instructions for the model to revise and improve its answer. We collect 1,260 interaction turns from 234 interaction sessions with three state-of-the-art LLMs. Each turn includes a user instruction, a model response, and a human evaluation of the model response. Through a detailed analysis of the collected responses, we find that all models struggle to incorporate new information into an existing answer, and to perform precise and unambiguous edits. Further, we find that models struggle to judge whether their outputs successfully followed user instructions, with accuracy at least 10 points short of human agreement. Our findings indicate that KIWI will be a valuable resource to measure progress and improve LLMs' instruction-following capabilities for knowledge intensive writing tasks.

KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions

This paper introduces the Decomposed Requirements Following Ratio (DRFR), a new metric for evaluating Large Language Models' (LLMs) ability to follow instructions. Addressing a gap in current methodologies, DRFR breaks down complex instructions into simpler criteria, facilitating a detailed analysis of LLMs' compliance with various aspects of tasks. Alongside this metric, we present InFoBench, a benchmark comprising 500 diverse instructions and 2,250 decomposed questions across multiple constraint categories. Our experiments compare DRFR with traditional scoring methods and explore annotation sources, including human experts, crowd-sourced workers, and GPT-4. The findings demonstrate DRFR's higher reliability and the effectiveness of using GPT-4 as a cost-efficient annotator. The evaluation of several advanced LLMs using this framework reveals their strengths and areas needing improvement, particularly in complex instruction-following. This study contributes a novel metric and benchmark, offering insights for future LLM development and evaluation.

Premium content

TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification

Downloads

Next from ACL 2024

Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES