Thailand

We present a new method for large language models to solve compositional tasks. Although they have shown strong performance on traditional language understanding tasks, large language models struggle to solve compositional tasks, where the solution depends on solving smaller instances of the same problem. We propose a natural approach to solve compositional tasks recursively. Our method, Re-Tuning, tunes models to break down a problem into subproblems, solve those subproblems, and combine the results. We show that our method significantly improves model performance on three representative compositional tasks: integer addition, dynamic programming, and parity. Compared to state-of-the-art methods that keep intermediate steps towards solving the problems, Re-Tuning achieves significantly higher accuracy and is more GPU memory efficient.

ACL 2024

Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning

length generalization

compositional

language model

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.

Pinyin input method engine (IME) refers to the transformation tool from pinyin sequence to Chinese characters, which is widely used on mobile phone applications. Due to the homophones, Pinyin IME suffers from the one-to-many mapping problem in the process of pinyin sequences to Chinese characters. To solve the above issue, this paper makes the first exploration to leverage an effective conditional variational mechanism (CVM) for pinyin IME. However, to ensure the stable and smooth operation of Pinyin IME under low-resource conditions (e.g., on offline mobile devices), we should balance diversity, accuracy, and efficiency with CVM, which is still challenging. To this end, we employ a novel strategy that simplifies the complexity of semantic encoding by facilitating the interaction between pinyin and the Chinese character information during the construction of continuous latent variables. Concurrently, the accuracy of the outcomes is enhanced by capitalizing on the discrete latent variables. Experimental results demonstrate the superior performance of our method.

Exploring Conditional Variational Mechanism to Pinyin Input Method for Addressing One-to-Many Mappings in Low-Resource Scenarios

The translation of gender-neutral person-referring terms (e.g.,the students) is often non-trivial.
Translating from English into German poses an interesting case---in German, person-referring nouns are usually gender-specific, and if the gender of the referent(s) is unknown or diverse, the generic masculine (die Studenten (m.)) is commonly used. 
This solution, however, reduces the visibility of other genders, such as women and non-binary people. To counteract gender discrimination, a societal movement towards using gender-fair language exists (e.g., by adopting neosystems). However, gender-fair German is currently barely supported in machine translation (MT), requiring post-editing or 
manual translations. We address this research gap by studying gender-fair language in English-to-German MT. Concretely, we enrich a community-created gender-fair language dictionary and sample multi-sentence test instances from encyclopedic text and parliamentary speeches.
Using these novel resources, we conduct the first benchmark study involving two commercial systems and six neural MT models for translating words in isolation and natural contexts across two domains. 
Our findings show that most systems produce mainly masculine forms and rarely gender-neutral variants, highlighting the need for future research. 
We release code and data at https://github.com/g8a9/building-bridges-gender-fair-german-mt.

Building Bridges: A Dataset for Evaluating Gender-Fair Machine Translation into German

Reinforcement Learning from Human Feedback (RLHF) leverages human preference data to train language models to align more closely with human essence. These human preference data, however, are labeled at the sequence level, creating a mismatch between sequence-level preference labels and tokens, which are autoregressively generated from the language model. Although several recent approaches have tried to provide token-level (i.e., dense) rewards for each individual token, these typically rely on predefined discrete reward values (e.g., positive: +1, negative: -1, neutral: 0), failing to account for varying degrees of preference inherent to each token. To address this limitation, we introduce TLCR (Token-Level Continuous Reward) for RLHF, which incorporates a discriminator trained to distinguish positive and negative tokens, and the confidence of the discriminator is used to assign continuous rewards to each token considering the context. Extensive experiments show that our proposed TLCR leads to consistent performance improvements over previous sequence-level or token-level discrete rewards on open-ended generation benchmarks.

TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback

We explore the ability of GPT-4 to perform ad-hoc schema-based information extraction from scientific literature. We assess specifically whether it can, with a basic one-shot prompting approach over the full text of the included manusciprts, replicate two existing material science datasets, one pertaining to multi-principal element alloys (MPEAs), and one to silicate diffusion. We collaborate with materials scientists to perform a detailed manual error analysis to assess where and why the model struggles to faithfully extract the desired information, and draw on their insights to suggest research directions to address this broadly important task.

Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Dataset

Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in diverse tasks across different domains, with an increasing focus on improving their zero-shot generalization capabilities for unseen multimodal tasks. Multimodal instruction tuning has emerged as a successful strategy for achieving zero-shot generalization by fine-tuning pre-trained models on diverse multimodal tasks through instructions. As MLLMs grow in complexity and size, the need for parameter-efficient fine-tuning methods like Low-Rank Adaption (LoRA), which fine-tunes with a minimal set of parameters, becomes essential. However, applying LoRA in multimodal instruction tuning presents the challenge of task interference, which leads to performance degradation, especially when dealing with a broad array of multimodal tasks. To address this, this paper introduces a novel approach that integrates multimodal instruction tuning with Conditional Mixture-of-LoRA (MixLoRA). It innovates upon LoRA by dynamically constructing low-rank adaptation matrices tailored to the unique demands of each input instance, aiming to mitigate task interference. Experimental results on various multimodal evaluation datasets indicate that MixLoRA not only outperforms the conventional LoRA with the same or even higher ranks, demonstrating its efficacy and adaptability in diverse multimodal tasks.

Multimodal Instruction Tuning with Conditional Mixture of LoRA

How can we train models to perform well on hard test data when hard training data is by definition difficult to label correctly? This question has been termed the scalable oversight problem and has drawn increasing attention as language models have continually improved. In this paper, we present the surprising conclusion that current pretrained language models often generalize relatively well from easy to hard data, even performing as well as oracle models finetuned on hard data. We demonstrate this kind of easy-to-hard generalization using simple finetuning methods like in-context learning, linear classifier heads, and QLoRA for seven different measures of datapoint hardness, including six empirically diverse human hardness measures (like grade level) and one model-based measure (loss-based). Furthermore, we show that even if one cares most about model performance on hard data, it can be better to collect easy data rather than hard data for finetuning, since hard data is generally noisier and costlier to collect. Our experiments use open models up to 70b in size and four publicly available question-answering datasets with questions ranging in difficulty from 3rd grade science questions to college level STEM questions and general-knowledge trivia. We conclude that easy-to-hard generalization in LMs is surprisingly strong for the tasks studied.

The Unreasonable Effectiveness of Easy Training Data for Hard Tasks

The successful adaptation of multilingual language models (LMs) to a specific language-task pair critically depends on the availability of data tailored for that condition. 
While cross-lingual transfer (XLT) methods have contributed to addressing this data scarcity problem, there still exists ongoing debate about the mechanisms behind their effectiveness.
In this work, we focus on one of promising assumptions about inner workings of XLT, that it encourages multilingual LMs to place greater emphasis on language-agnostic or task-specific features. 
We test this hypothesis by examining how the patterns of XLT change with a varying number of source languages involved in the process.
Our experimental findings show that the use of multiple source languages in XLT-a technique we term Multi-Source Language Training (MSLT)-leads to increased mingling of embedding spaces for different languages, supporting the claim that XLT benefits from making use of language-independent information. 
On the other hand, we discover that using an arbitrary combination of source languages does not always guarantee better performance. We suggest simple heuristics for identifying effective language combinations for MSLT and empirically prove its effectiveness.

Analysis of Multi-Source Language Training in Cross-Lingual Transfer

How do we roll out language technologies across a world with 7,000 languages? In one story, we scale the successes of NLP further into `low-resource' languages, doing ever more with less. However, this approach does not recognise the fact that, beyond the 500 institutional languages, the remaining languages are oral vernaculars spoken by communities who use a language of wider communication to interact with the outside world. I argue that such `contact languages' are the appropriate target for technologies like machine translation, and that the 6,500 oral languages must be approached differently. I share a story from an Indigenous community, where local people reshaped an extractive agenda to align with their relational agenda. I describe the emerging paradigm of relational NLP and explain how it opens the way to non-extractive methods and to solutions that enhance human agency.

Must NLP be Extractive?

We examine whether large language models (LLMs) exhibit race- and gender-based name discrimination in hiring decisions, similar to classic findings in the social sciences (Bertrand and Mullainathan, 2004). We design a series of templatic prompts to LLMs to write an email to a named job applicant informing them of a hiring decision. By manipulating the applicant's first name, we measure the effect of perceived race, ethnicity, and gender on the probability that the LLM generates an acceptance or rejection email. We find that the hiring decisions of LLMs in many settings are more likely to favor White applicants over Hispanic applicants. In aggregate, the groups with the highest and lowest acceptance rates respectively are masculine White names and masculine Hispanic names. However, the comparative acceptance rates by group vary under different templatic settings, suggesting that LLMs' race- and gender-sensitivity may be idiosyncratic and prompt-sensitive.

Do Large Language Models Discriminate in Hiring Decisions on the Basis of Race, Ethnicity, and Gender?

In this study, we investigate the capabilities and inherent biases of advanced large language models (LLMs) such as GPT-3.5 and GPT-4 in the context of debate evaluation. We discover that LLM's performance exceeds humans and surpasses the performance of state-of-the-art methods fine-tuned on extensive datasets. We additionally explore and analyze biases present in LLMs, including positional bias, lexical bias, order bias, which may affect their evaluative judgments. Our findings reveal a consistent bias in both GPT-3.5 and GPT-4 towards the second candidate response presented, attributed to prompt design. We also uncover a lexical bias in both GPT-3.5 and GPT-4, especially when label sets carry connotations such as numerical or sequential, highlighting the critical need for careful label verbalizer selection in prompt design. Additionally, our analysis indicates a tendency of both models to favor the debate's concluding side as the winner, suggesting an end-of-discussion bias.

Premium content

Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning

Downloads

Next from ACL 2024

Exploring Conditional Variational Mechanism to Pinyin Input Method for Addressing One-to-Many Mappings in Low-Resource Scenarios

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES