arXiv subjects

Antoine Bosselut

Publications and source records attributed to Antoine Bosselut.

At least 73 records · Page 4Linked to original sources

arXiv2024

Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning

Large language models (LLMs) have been shown to perform better when asked to reason step-by-step before answering a question. However, it is unclear to what degree the model's final answer is faithful to the stated reasoning steps. In this paper, we perform a causal mediation analysis on twelve LLMs to examine how intermediate reasoning steps generated by the LLM influence the final outcome and find that LLMs do not reliably use their intermediate reasoning steps when generating an answer. To address this issue, we introduce FRODO, a framework to tailor small-sized LMs to generate correct reasoning steps and robustly reason over these steps. FRODO consists of an inference module that learns to generate correct reasoning steps using an implicit causal reward function and a reasoning module that learns to faithfully reason over these intermediate inferences using a counterfactual and causal preference objective. Our experiments show that FRODO significantly outperforms four competitive baselines. Furthermore, FRODO improves the robustness and generalization ability of the reasoning LM, yielding higher performance on out-of-distribution test sets. Finally, we find that FRODO's rationales are more faithful to its final answer predictions than standard supervised fine-tuning.

cs.CL↗

arXiv2024

"Flex Tape Can't Fix That": Bias and Misinformation in Edited Language Models

Model editing has emerged as a cost-effective strategy to update knowledge stored in language models. However, model editing can have unintended consequences after edits are applied: information unrelated to the edits can also be changed, and other general behaviors of the model can be wrongly altered. In this work, we investigate how model editing methods unexpectedly amplify model biases post-edit. We introduce a novel benchmark dataset, Seesaw-CF, for measuring bias-related harms of model editing and conduct the first in-depth investigation of how different weight-editing methods impact model bias. Specifically, we focus on biases with respect to demographic attributes such as race, geographic origin, and gender, as well as qualitative flaws in long-form texts generated by edited language models. We find that edited models exhibit, to various degrees, more biased behavior as they become less confident in attributes for Asian, African, and South American subjects. Furthermore, edited models amplify sexism and xenophobia in text generations while remaining seemingly coherent and logical. Finally, editing facts about place of birth, country of citizenship, or gender have particularly negative effects on the model's knowledge about unrelated features like field of work.

cs.CL↗

arXiv2024

DiffuCOMET: Contextual Commonsense Knowledge Diffusion

Inferring contextually-relevant and diverse commonsense to understand narratives remains challenging for knowledge models. In this work, we develop a series of knowledge models, DiffuCOMET, that leverage diffusion to learn to reconstruct the implicit semantic connections between narrative contexts and relevant commonsense knowledge. Across multiple diffusion steps, our method progressively refines a representation of commonsense facts that is anchored to a narrative, producing contextually-relevant and diverse commonsense inferences for an input context. To evaluate DiffuCOMET, we introduce new metrics for commonsense inference that more closely measure knowledge diversity and contextual relevance. Our results on two different benchmarks, ComFact and WebNLG+, show that knowledge generated by DiffuCOMET achieves a better trade-off between commonsense diversity, contextual relevance and alignment to known gold references, compared to baseline knowledge models.

cs.CL↗

arXiv2024

ConGeo: Robust Cross-view Geo-localization across Ground View Variations

Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view. In real-world scenarios, the task requires accommodating diverse ground images captured by users with varying orientations and reduced field of views (FoVs). However, existing learning pipelines are orientation-specific or FoV-specific, demanding separate model training for different ground view variations. Such models heavily depend on the North-aligned spatial correspondence and predefined FoVs in the training data, compromising their robustness across different settings. To tackle this challenge, we propose ConGeo, a single- and cross-view Contrastive method for Geo-localization: it enhances robustness and consistency in feature representations to improve a model's invariance to orientation and its resilience to FoV variations, by enforcing proximity between ground view variations of the same location. As a generic learning objective for cross-view geo-localization, when integrated into state-of-the-art pipelines, ConGeo significantly boosts the performance of three base models on four geo-localization benchmarks for diverse ground view variations and outperforms competing methods that train separate models for each ground view variation.

cs.CV↗

arXiv2024

Instruction-tuning Aligns LLMs to the Human Brain

Instruction-tuning is a widely adopted finetuning method that enables large language models (LLMs) to generate output that more closely resembles human responses. However, no studies have shown that instruction-tuning actually teaches LLMs to process language in a similar manner as humans. We investigate the effect of instruction-tuning on aligning LLM and human language processing mechanisms in two ways: (1) brain alignment, the similarity of LLM internal representations to neural activity in the human language system, and (2) behavioral alignment, the similarity of LLM and human behavior on a reading task. We assess 25 vanilla and instruction-tuned LLMs on three datasets involving humans reading naturalistic stories and sentences, and find that instruction-tuning generally enhances brain alignment (~6%), but has no similar effect on behavioral alignment. To identify factors underlying this improvement in brain alignment, we compute correlations between brain alignment and various LLM properties, such as model size, problem-solving, and world knowledge understanding. Notably, we find a strong positive correlation between brain alignment and model size (r = 0.95), as well as performance on tasks requiring world knowledge (r = 0.81). Our results demonstrate that instruction-tuning LLMs improves both world knowledge representations and brain alignment, suggesting that the mechanisms that encode world knowledge in LLMs also improve representational alignment to the human brain.

cs.CL↗

arXiv2024

Exploring Defeasibility in Causal Reasoning

Defeasibility in causal reasoning implies that the causal relationship between cause and effect can be strengthened or weakened. Namely, the causal strength between cause and effect should increase or decrease with the incorporation of strengthening arguments (supporters) or weakening arguments (defeaters), respectively. However, existing works ignore defeasibility in causal reasoning and fail to evaluate existing causal strength metrics in defeasible settings. In this work, we present $δ$-CAUSAL, the first benchmark dataset for studying defeasibility in causal reasoning. $δ$-CAUSAL includes around 11K events spanning ten domains, featuring defeasible causality pairs, i.e., cause-effect pairs accompanied by supporters and defeaters. We further show current causal strength metrics fail to reflect the change of causal strength with the incorporation of supporters or defeaters in $δ$-CAUSAL. To this end, we propose CESAR (Causal Embedding aSsociation with Attention Rating), a metric that measures causal strength based on token-level causal relationships. CESAR achieves a significant 69.7% relative improvement over existing metrics, increasing from 47.2% to 80.1% in capturing the causal strength change brought by supporters and defeaters. We further demonstrate even Large Language Models (LLMs) like GPT-3.5 still lag 4.5 and 10.7 points behind humans in generating supporters and defeaters, emphasizing the challenge posed by $δ$-CAUSAL.

cs.CL↗

arXiv2024

Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs

Event commonsense reasoning requires the ability to reason about the relationship between events, as well as infer implicit context underlying that relationship. However, data scarcity makes it challenging for language models to learn to generate commonsense inferences for contexts and questions involving interactions between complex events. To address this demand, we present COM2 (COMplex COMmonsense), a new dataset created by sampling multi-hop logical queries (e.g., the joint effect or cause of both event A and B, or the effect of the effect of event C) from an existing commonsense knowledge graph (CSKG), and verbalizing them using handcrafted rules and large language models into multiple-choice and text generation questions. Our experiments show that language models trained on COM2 exhibit significant improvements in complex reasoning ability, resulting in enhanced zero-shot performance in both in-domain and out-of-domain tasks for question answering and generative commonsense reasoning, without expensive human annotations. Code and data are available at https://github.com/tqfang/complex-commonsense-reasoning.

cs.CL↗

arXiv2024

Brain-Like Language Processing via a Shallow Untrained Multihead Attention Network

Large Language Models (LLMs) have been shown to be effective models of the human language system, with some models predicting most explainable variance of brain activity in current datasets. Even in untrained models, the representations induced by architectural priors can exhibit reasonable alignment to brain data. In this work, we investigate the key architectural components driving the surprising alignment of untrained models. To estimate LLM-to-brain similarity, we first select language-selective units within an LLM, similar to how neuroscientists identify the language network in the human brain. We then benchmark the brain alignment of these LLM units across five different brain recording datasets. By isolating critical components of the Transformer architecture, we identify tokenization strategy and multihead attention as the two major components driving brain alignment. A simple form of recurrence further improves alignment. We further demonstrate this quantitative brain alignment of our model by reproducing landmark studies in the language neuroscience field, showing that localized model units -- just like language voxels measured empirically in the human brain -- discriminate more reliably between lexical than syntactic differences, and exhibit similar response profiles under the same experimental conditions. Finally, we demonstrate the utility of our model's representations for language modeling, achieving improved sample and parameter efficiency over comparable architectures. Our model's estimates of surprisal sets a new state-of-the-art in the behavioral alignment to human reading times. Taken together, we propose a highly brain- and behaviorally-aligned model that conceptualizes the human language system as an untrained shallow feature encoder, with structural priors, combined with a trained decoder to achieve efficient and performant language processing.

cs.CL↗

arXiv2024

ComperDial: Commonsense Persona-grounded Dialogue Dataset and Benchmark

We propose a new benchmark, ComperDial, which facilitates the training and evaluation of evaluation metrics for open-domain dialogue systems. ComperDial consists of human-scored responses for 10,395 dialogue turns in 1,485 conversations collected from 99 dialogue agents submitted to the Commonsense Persona-grounded Dialogue (CPD) challenge. As a result, for any dialogue, our benchmark includes multiple diverse responses with variety of characteristics to ensure more robust evaluation of learned dialogue metrics. In addition to single-turn response scores, ComperDial also contains dialogue-level human-annotated scores, enabling joint assessment of multi-turn model responses throughout a dialogue. Finally, building off ComperDial, we devise a new automatic evaluation metric to measure the general similarity of model-generated dialogues to human conversations. Our experimental results demonstrate that our novel metric, CPDScore is more correlated with human judgments than existing metrics. We release both ComperDial and CPDScore to the community to accelerate development of automatic evaluation metrics for open-domain dialogue systems.

cs.CL↗

arXiv2024

Course Recommender Systems Need to Consider the Job Market

Current course recommender systems primarily leverage learner-course interactions, course content, learner preferences, and supplementary course details like instructor, institution, ratings, and reviews, to make their recommendation. However, these systems often overlook a critical aspect: the evolving skill demand of the job market. This paper focuses on the perspective of academic researchers, working in collaboration with the industry, aiming to develop a course recommender system that incorporates job market skill demands. In light of the job market's rapid changes and the current state of research in course recommender systems, we outline essential properties for course recommender systems to address these demands effectively, including explainable, sequential, unsupervised, and aligned with the job market and user's goals. Our discussion extends to the challenges and research questions this objective entails, including unsupervised skill extraction from job listings, course descriptions, and resumes, as well as predicting recommendations that align with learner objectives and the job market and designing metrics to evaluate this alignment. Furthermore, we introduce an initial system that addresses some existing limitations of course recommender systems using large Language Models (LLMs) for skill extraction and Reinforcement Learning (RL) for alignment with the job market. We provide empirical results using open-source data to demonstrate its effectiveness.

cs.IR↗

arXiv2024

A Design Space for Intelligent and Interactive Writing Assistants

In our era of rapid technological advancement, the research landscape for writing assistants has become increasingly fragmented across various research communities. We seek to address this challenge by proposing a design space as a structured way to examine and explore the multidimensional space of intelligent and interactive writing assistants. Through a large community collaboration, we explore five aspects of writing assistants: task, user, technology, interaction, and ecosystem. Within each aspect, we define dimensions (i.e., fundamental components of an aspect) and codes (i.e., potential options for each dimension) by systematically reviewing 115 papers. Our design space aims to offer researchers and designers a practical tool to navigate, comprehend, and compare the various possibilities of writing assistants, and aid in the envisioning and design of new writing assistants.

cs.HC↗

arXiv2024

ConVQG: Contrastive Visual Question Generation with Multimodal Guidance

Asking questions about visual environments is a crucial way for intelligent agents to understand rich multi-faceted scenes, raising the importance of Visual Question Generation (VQG) systems. Apart from being grounded to the image, existing VQG systems can use textual constraints, such as expected answers or knowledge triplets, to generate focused questions. These constraints allow VQG systems to specify the question content or leverage external commonsense knowledge that can not be obtained from the image content only. However, generating focused questions using textual constraints while enforcing a high relevance to the image content remains a challenge, as VQG systems often ignore one or both forms of grounding. In this work, we propose Contrastive Visual Question Generation (ConVQG), a method using a dual contrastive objective to discriminate questions generated using both modalities from those based on a single one. Experiments on both knowledge-aware and standard VQG benchmarks demonstrate that ConVQG outperforms the state-of-the-art methods and generates image-grounded, text-guided, and knowledge-rich questions. Our human evaluation results also show preference for ConVQG questions compared to non-contrastive baselines.

cs.CV↗

arXiv2024

Rethinking Skill Extraction in the Job Market Domain using Large Language Models

Skill Extraction involves identifying skills and qualifications mentioned in documents such as job postings and resumes. The task is commonly tackled by training supervised models using a sequence labeling approach with BIO tags. However, the reliance on manually annotated data limits the generalizability of such approaches. Moreover, the common BIO setting limits the ability of the models to capture complex skill patterns and handle ambiguous mentions. In this paper, we explore the use of in-context learning to overcome these challenges, on a benchmark of 6 uniformized skill extraction datasets. Our approach leverages the few-shot learning capabilities of large language models (LLMs) to identify and extract skills from sentences. We show that LLMs, despite not being on par with traditional supervised models in terms of performance, can better handle syntactically complex skill mentions in skill extraction tasks.

cs.CL↗

arXiv2024

JOBSKAPE: A Framework for Generating Synthetic Job Postings to Enhance Skill Matching

Recent approaches in skill matching, employing synthetic training data for classification or similarity model training, have shown promising results, reducing the need for time-consuming and expensive annotations. However, previous synthetic datasets have limitations, such as featuring only one skill per sentence and generally comprising short sentences. In this paper, we introduce JobSkape, a framework to generate synthetic data that tackles these limitations, specifically designed to enhance skill-to-taxonomy matching. Within this framework, we create SkillSkape, a comprehensive open-source synthetic dataset of job postings tailored for skill-matching tasks. We introduce several offline metrics that show that our dataset resembles real-world data. Additionally, we present a multi-step pipeline for skill extraction and matching tasks using large language models (LLMs), benchmarking against known supervised methodologies. We outline that the downstream evaluation results on real-world data can beat baselines, underscoring its efficacy and adaptability.

cs.CL↗

arXiv2024

REFINER: Reasoning Feedback on Intermediate Representations

Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e.g., chain-of-thought prompting. However, these intermediate inference steps may be inappropriate deductions from the initial context and lead to incorrect final predictions. Here we introduce REFINER, a framework for finetuning LMs to explicitly generate intermediate reasoning steps while interacting with a critic model that provides automated feedback on the reasoning. Specifically, the critic provides structured feedback that the reasoning LM uses to iteratively improve its intermediate arguments. Empirical evaluations of REFINER on three diverse reasoning tasks show significant improvements over baseline LMs of comparable scale. Furthermore, when using GPT-3.5 or ChatGPT as the reasoner, the trained critic significantly improves reasoning without finetuning the reasoner. Finally, our critic model is trained without expensive human-in-the-loop data but can be substituted with humans at inference time.

cs.CL↗

arXiv2023

MEDITRON-70B: Scaling Medical Pretraining for Large Language Models

Large language models (LLMs) can potentially democratize access to medical knowledge. While many efforts have been made to harness and improve LLMs' medical knowledge and reasoning capacities, the resulting models are either closed-source (e.g., PaLM, GPT-4) or limited in scale (<= 13B parameters), which restricts their abilities. In this work, we improve access to large-scale medical LLMs by releasing MEDITRON: a suite of open-source LLMs with 7B and 70B parameters adapted to the medical domain. MEDITRON builds on Llama-2 (through our adaptation of Nvidia's Megatron-LM distributed trainer), and extends pretraining on a comprehensively curated medical corpus, including selected PubMed articles, abstracts, and internationally-recognized medical guidelines. Evaluations using four major medical benchmarks show significant performance gains over several state-of-the-art baselines before and after task-specific finetuning. Overall, MEDITRON achieves a 6% absolute performance gain over the best public baseline in its parameter class and 3% over the strongest baseline we finetuned from Llama-2. Compared to closed-source LLMs, MEDITRON-70B outperforms GPT-3.5 and Med-PaLM and is within 5% of GPT-4 and 10% of Med-PaLM-2. We release our code for curating the medical pretraining corpus and the MEDITRON model weights to drive open-source development of more capable medical LLMs.

cs.CL↗

arXiv2023

CRAB: Assessing the Strength of Causal Relationships Between Real-world Events

Understanding narratives requires reasoning about the cause-and-effect relationships between events mentioned in the text. While existing foundation models yield impressive results in many NLP tasks requiring reasoning, it is unclear whether they understand the complexity of the underlying network of causal relationships of events in narratives. In this work, we present CRAB, a new Causal Reasoning Assessment Benchmark designed to evaluate causal understanding of events in real-world narratives. CRAB contains fine-grained, contextual causality annotations for ~2.7K pairs of real-world events that describe various newsworthy event timelines (e.g., the acquisition of Twitter by Elon Musk). Using CRAB, we measure the performance of several large language models, demonstrating that most systems achieve poor performance on the task. Motivated by classical causal principles, we also analyze the causal structures of groups of events in CRAB, and find that models perform worse on causal reasoning when events are derived from complex causal structures compared to simple linear causal chains. We make our dataset and code available to the research community.

cs.CL↗

arXiv2023

RECKONING: Reasoning through Dynamic Knowledge Encoding

Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered for a particular question, in-context reasoning can be sensitive to distractor facts, additional content that is irrelevant to a question but that may be relevant for a different question (i.e., not necessarily random noise). In these situations, the model fails to distinguish the knowledge that is necessary to answer the question, leading to spurious reasoning and degraded performance. This reasoning failure contrasts with the model's apparent ability to distinguish its contextual knowledge from all the knowledge it has memorized during pre-training. Following this observation, we propose teaching the model to reason more robustly by folding the provided contextual knowledge into the model's parameters before presenting it with a question. Our method, RECKONING, is a bi-level learning algorithm that teaches language models to reason by updating their parametric knowledge through back-propagation, allowing them to then answer questions using the updated parameters. During training, the inner loop rapidly adapts a copy of the model weights to encode contextual knowledge into its parameters. In the outer loop, the model learns to use the updated weights to reproduce and answer reasoning questions about the memorized knowledge. Our experiments on two multi-hop reasoning datasets show that RECKONING's performance improves over the in-context reasoning baseline (by up to 4.5%). We also find that compared to in-context reasoning, RECKONING generalizes better to longer reasoning chains unseen during training, is more robust to distractors in the context, and is more computationally efficient when multiple questions are asked about the same knowledge.

cs.CL↗